Ordered by Author


Order by: Date  | Author  | Title  | Index of all authors  | Index of Pixar Technical Memos


Reduced Boundary Viscosity for Smoke

Alexis Angelidis
June 2019

We propose a method to reduce viscosity at the boundaries of incompressible flows. Our method allows artists to control the amount of boundary viscosity by mixing a new slip boundary solution with an existing no-slip solution. The cost of our method is an additional pre-computation and a post-computation that can ... more

Paper (PDF)

Available as Pixar Technical Memo #19-02


Vorticle Fluid Simulation

Alexis Angelidis
February 2015

We present a Lagrangian method for simulating incompressible gases in 3 dimensions. Using the vorticity equation with Lagrangian particles, we create, modify and delete vortices of varying size in a manner that handles buoyancy, boundaries, viscosity and collision with deformable objects using monopoles. Our method scales linearly for parallel processing and provides user controls at varying ... more

Paper (PDF)

Available as Pixar Technical Memo #15-01


Kernel-Predicting Convolutional Networks for Denoising Monte Carlo Renderings

Steve Bako, Thijs Vogels, Brian McWilliams, Mark Meyer, Jan Novak, Alex Harvill, Pradeep Sen, Tony DeRose, Fabrice Rousselle
July 2017

Regression-based algorithms have shown to be good at denoising Monte Carlo (MC) renderings by leveraging its inexpensive by-products (e.g., feature buffers). However, when using higher-order models to handle complex cases, these techniques often overfit to noise in the input. For this reason, supervised learning methods have been proposed that ... more

Paper (PDF)

SIGGRAPH 2017


Untangling Cloth

David Baraff, Andrew Witkin, Michael Kass
August 2003

Deficient cloth-to-cloth collision response is the most serious shortcoming of most cloth simulation systems. Past approaches to cloth-cloth collision have used history to decide wheter nearby cloth regions have interpenetrated. The biggest pitfall of history-based methods is that an error anywhere along the way can give rise to persistent tangles...This ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 2003


A Procedural Approach for Stylized Bark Shading

Alec Bartsch, Colin Thompson, Fernando de Goes
May 2023

The Earth characters in Pixar's feature film Elemental (2023) called for a stylized look with bark patterns resembling organic locks of hair. To scale this custom shading to an entire class of background characters, we implemented an artistic-driven procedural workflow that offered rapid iterations on pattern generation without requiring extensive ... more

Paper (PDF)

SIGGRAPH Talks 2023


Automating the Handmade: Shading Thousands of Garments for Coco

Byron Bashforth, Fernando de Goes, Jacob Kuenzel, Jake Merrell, Athena Xenakis
August 2018

Coco presented a challenge for the garment shading team. Firstly, the scale of the movie is significant with both the human and skeleton worlds filled with primary, secondary, and background characters. Secondly, the garments speak to a specific culture and our shading needed to be very detailed to ... more

Paper (PDF)


RenderMan, Theory and Practice

Dana Batali, Byron Bashforth, Chris Bernardi, Per H. Christensen, David Laur, Christophe Hery, Guido Quaroni, Erin Tomson, Thomas Jordan, Wayne Wooten
July 2003

Siggraph 2003 course notes.

Paper (PDF)


Computing Smooth Surface Contours with Accurate Topology

Pierre Benard, Aaron Hertzmann, Michael Kass
March 2014

This paper introduces a method for accurately computing the visible contours of a smooth 3D surface for stylization. This is a surprisingly difficult problem, and previous methods are prone to topological errors, such as gaps in the outline. Our approach is to generate, for each viewpoint, a new triangle mesh with contours that are topologically-equivalent ... more

Paper (PDF)

To appear in ACM Transactions on Graphics


Stylizing Animation By Example

Pierre Benard, Forrester Cole, Michael Kass, Igor Mordatch, James Hegarty, Martin Sebastian Senn, Kurt Fleischer, Davide Pesare, Katherine Breeden
April 2013

Skilled artists, using traditional media or modern computer painting tools, can create a variety of expressive styles that are very appealing in still images, but have been unsuitable for animation. The key difficulty is that existing techniques lack adequate temporal coherence to animate these styles effectively. Here we augment the ... more

Paper (PDF)

Additional materials: [ComputerGraphicsWorldArticle.pdf], [PaintTweenDistro.tgz], [PaintTweenWorkingSets.tgz], [additionalResults.mov], [mainVideo.mov]

Available in the proceedings of SIGGRAPH 2013.

Available as Pixar Technical Memo #13-03


Rat-Sized Water Effects in Ratatouille

Gary Bruins, Jon Reisch
May 2007

A particularly heavy effects sequence in the film Ratatouille depicts a colony of rats fleeing their home and crossing a long narrow river in several makeshift boats during a rainy afternoon. Nearly the entire sequence was photographed inches above the ground from a s perspective. Although this perspective provided a very interesting point of view ... more

Paper (PDF)

Available as Pixar Technical Memo #07-14


Optimal Voronoi Tessellations with Hessian-based Anisotropy

Max Budninskiy, Beibei Liu, Fernando de Goes, Yiying Tong, Pierre Alliez, Mathieu Desbrun
December 2016

This paper presents a variational method to generate cell complexes with local anisotropy conforming to the Hessian of any given convex function and for any given local mesh density. Our formulation builds upon approximation theory to offer an anisotropic extension of Centroidal Voronoi Tessellations which can be seen as a ... more

Paper (PDF)

Additional materials: [BLdG+16_SuppMat.pdf]

SIGGRAPH Asia 2016


Acting with Contact in Ratatouille - Cartoon Collision and Response

Gordon Cameron, Robert Russ, Adam Woodbury
May 2007

Contact is natural in the real world but often avoided in 3D animated features. Animators tend to make acting decisions that minimise or avoid contact within and between their characters and the world, and when apparent contact does occur, it can tend to feel both "floaty" and unrealistic. "Ratatouille" called for dynamic, tactile characters that ... more

Paper (PDF)

Available as Pixar Technical Memo #07-10


Dispersion Kernels for Water Wave Simulation

Jose Angel Canabal, David Miraut, Nils Thuerey, Theodore Kim, Javier Portilla, Miguel Otaduy
December 2016

We propose a method to simulate the rich, scale-dependent dynamics of water waves. Our method preserves the dispersion properties of real waves, yet it supports interactions with obstacles and is computationally efficient. Fundamentally, it computes wave accelerations by way of applying a dispersion kernel as a spatially variant filter, which ... more

Paper (PDF)


Anyone Can Cook -- Inside Ratatouille's Kitchen

Jun Han Cho, Athena Xenakis, Stefan Gronsky, Apurva Shah
July 2007

The passion for cooking and food are the central theme of Pixar's recent film - Ratatouille. This complex and multi-faceted problem posed many challenges that were solved using diverse computer graphics and production techniques. In this course we will comprehensively cover all aspects including modeling, dressing, shading, lighting and effects.

The ... more

Paper (PDF)

Available as Siggraph 2007 Course Notes, Course Number 30


Progressive Multi-Jittered Sample Sequences

Per Christensen, Andrew Kensler, Charlie Kilpatrick
July 2018

We introduce three new families of stochastic algorithms to generate progressive 2D sample point sequences. This opens a general framework that researchers and practitioners may find useful when developing future sample sequences. Our best sequences have the same low sampling error as the best known sequence (a particular randomization of ... more

Paper (PDF)

Additional materials: [pmj_slides.pdf], [pmj_suppl.pdf]

Computer Graphics Forum (Proceedings of the Eurographics Symposium on Rendering 2018)


RenderMan: An Advanced Path Tracing Architecture for Movie Rendering

Per Christensen, Julian Fong, Jonathan Shade, Wayne Wooten, Brenden Schubert, Andrew Kensler, Stephen Friedman, Charlie Kilpatrick, Cliff Ramshaw, Marc Bannister, Brenton Rayner, Jonathan Brouillat, Max Liani
July 2018

Pixar's RenderMan renderer is used to render all of Pixar's films, and by many film studios to render visual effects for live-action movies. RenderMan started as a scanline renderer based on the Reyes algorithm, and was extended over the years with ray tracing and several global illumination algorithms. This paper describes the modern version of ... more

Paper (PDF)


Progressive Sampling Strategies for Disk Light Sources

Per Christensen
June 2018

This technical memo compares six different strategies for sampling a disk area light source. We test padding the domain with zero values, rejection sampling, polar mapping, concentric mapping, and two new strategies we call polar4 and concentric4 mapping. We test the six strategies with nine different sample sequences ... more

Paper (PDF)

Available as Pixar Technical Memo #18-02


The Path to Path-Traced Movies

Per H. Christensen, Wojciech Jarosz
October 2016

Path tracing is one of several techniques to render photorealistic images by simulating the physics of light propagation within a scene. The roots of path tracing are outside of computer graphics, in the Monte Carlo simulations developed for neutron transport. A great strength of path tracing is that it is conceptually, mathematically, and often-times algorithmically ... more

Paper (PDF)

Appeared as: Foundation and Trends in Computer Graphics and Vision, volume 10, number 2, pages 103-175.


Approximate Reflectance Profiles for Efficient Subsurface Scattering

Per H. Christensen, Brent Burley
July 2015

We present three useful parameterizations of a BSSRDF model based on empirical reflectance profiles. The model is very simple, but with the appropriate parameterization it matches brute-force Monte Carlo references better than state-of-the-art physically-based models (quantized diffusion and photon beam diffusion) for many common materials. Each reflectance profile is a sum of ... more

Paper (PDF)

Additional materials: [SIGGRAPH_Tech_Talk.pdf], [approxbssrdfslides.pdf]

Available as Pixar Technical Memo #15-04


Multiresolution Radiosity Caching for Efficient Preview and Final Quality Global Illumination in Movies

Per H. Christensen, George Harker, Jonathan Shade, Brenden Schubert, Dana Batali
July 2012

We present a multiresolution radiosity caching method that allows global illumination to be computed efficiently in a single pass in complex CG movie production scenes.

For distribution ray tracing in production scenes, the bottleneck is the time spent evaluating complex shaders at the ray hit points. We speed up this shader ... more

Paper (PDF)

Additional materials: [globillum.m4v], [siggraphslides.pdf], [siggraphtalk.pdf], [subsurf.m4v]

Available as Pixar Technical Memo #12-06


Point-Based Global Illumination for Movie Production

Per H. Christensen
July 2010

This course note describes a fast point-based method for computing diffuse and glossy global illumination, area light illumination and soft shadows, HDRI environment map illumination, multiple diffuse reflection bounces, final gathering for photon mapping, ambient occlusion, reflection occlusion, and volume scattering. The results are free of noise and the ... more

Paper (PDF)

Additional materials: [Slides.pdf]


Point-Based Approximate Color Bleeding

Per H. Christensen
July 2008

This technical memo describes a fast point-based method for computing diffuse global illumination (color bleeding). The computation is 4-10 times faster than ray tracing, uses less memory, has no noise, and its run-time does not increase due to displacement-mapped surfaces, complex shaders, or many complex light sources. These properties make the method suitable ... more

Paper (PDF)

Additional materials: [SlidesFromAnnecy09.pdf]

Available as Pixar Technical Memo #08-01


Ray Tracing for the Movie 'Cars'

Per H. Christensen, Julian Fong, David M. Laur, Dana Batali
September 2006

This paper describes how we extended Pixar's RenderMan renderer with ray tracing abilities. In order to ray trace highly complex scenes we use multiresolution geometry and texture caches, and use ray differentials to determine the appropriate resolution. With this method we are able to efficiently ray trace scenes with much more geometry and ... more

Paper (PDF)

Available in Proceedings of the IEEE Symposium on Interactive Ray Tracing 2006, pages 1-6. IEEE 2006


An Irradiance Atlas for Global Illumination in Complex Production Scenes

Per H. Christensen, Dana Batali
June 2004

We introduce a tiled 3D MIP map representation of global illumination data. The representation is an adaptive sparse octree with a "brick" at each octree node; each brick consists of 8 cubed voxels with sparse irradiance values. The representation is designed to enable efficient caching. Combined with ... more

Paper (PDF)

Published as pp. 133-141 in the Proceedings of the Eurographics Symposium on Rendering 2004, Eurographics/ACM, June 2004.


Ray Differentials and Multiresolution Geometry Caching for Distribution Ray Tracing in Complex Scenes

Per H. Christensen, David M. Laur, Julian Fong, Wayne L. Wooten, Dana Batali
September 2003

When rendering only directly visible objects, ray tracing a few levels of specular reflection from large, low curvatures surfaces, and ray tracing shadows from point-like light sources, the accessed geometry is coherent and a geometry cache performs well. But in many other cases, ... more

Paper (PDF)

Published as pp. pp. 543-552 in Computer Graphics Forum (Eurographics 2003 Conference Proceedings), Blackwell Publishers, September 2003.


Adjoints and Importance in Rendering: an Overview

Per H. Christensen
July 2003

This survey gives an overview of the use of importance, an adjoint of light, in speeding up rendering. The importance of a light distribution indicates its contribution to the region of most interest --- typically the directly visible parts of a scene. Importance can therefore be used to concentrate global illumination and ray ... more

Paper (PDF)

Available as IEEE Transactions on Visualization and Computer Graphics (TVCG), Volume 9, Number 3, pages 329-340. IEEE, July 2003.


Making Souls: Methods and a Pipeline for Volumetric Characters

Patrick Coleman, Laura Murphy, Markus Kranzler, Max Gilbert
June 2020

The soul characters in Disney/Pixar's Soul have a stylized appearance that sets them into a unique world, which introduced many new challenges. Everyone from the art department and character modelers and shaders to the technical directors and developers in the effects, lighting, and software groups collaborated to bring this new ... more

Paper (PDF)

Video


Into the Voyd: Teleportation of Light Transport in Incredibles 2

Patrick Coleman, Darwyn Peachey, Tom Nettleship, Ryusuke Villemin, Tobin Jones
August 2018

In Incredibles 2, a character named Voyd has the ability to create portals that connect two locations in space. A particular challenge for this film is the presence of portals in a number of fast-paced action sequences with multiple characters and objects passing through them, causing multiple views of ... more

Paper (PDF)

Additional materials: [digiproPortals.mov]


Chop It Up! Animation-Driven Modeling, Simulation, and Shading in the Kitchen

Patrick Coleman, Eric Froemling
May 2007

In Disney/Pixar's Ratatouille, the creation of believable cooking environments with all their complexity has been an important element in presenting a rich world that helps draw the audience into the story. Part of that complexity arises in the preparation of food before cooking. To create complex animations of food in preparation, we designed a system ... more

Paper (PDF)

Available as Pixar Technical Memo #07-13


3D Paint Baking Proposal

Robert L. Cook
May 2007

3d paint has long been one of the most expensive parts of rendering at Pixar. This proposal is for a new baking technique that would greatly reduce the run-time cost of 3d paint and require no changes to the existing workflow. The implementation makes heavy use of existing code, which ... more

Paper (PDF)

Available as Pixar Technical Memo #07-16


Stochastic Simplification of Aggregate Detail

Robert L. Cook, John Halstead, Maxwell Planck, David Ryu
May 2007

Many renderers perform poorly on scenes that contain a lot of detailed geometry. The load on the renderer can be alleviated by simplification techniques, which create less expensive representations of geometry that is small on the screen. Current simplification techniques for high-quality surface-based rendering tend to work best with element ... more

Paper (PDF)

Additional materials: [SiggraphSlides.pdf], [WithAndWithoutSimplification.mov]

Available in the Proceedings of Siggraph 2007.

Available as Pixar Technical Memo #06-05a

Other versions:


Wavelet Noise

Robert L. Cook, Tony DeRose
August 2005

Noise functions are an essential building block for writing procedural shaders in 3D computer graphics. The original noise function introduced by Ken Perlin is still the most popular because it is simple and fast, and many spectacular images have been made ... more

Paper (PDF)

Additional materials: [RapLyrics.txt]

Available in the Proceedings of SIGGRAPH 2005


The Reyes Rendering Architecture

Robert L. Cook, Loren Carpenter, Edwin Catmull
July 1987

An architecture is presented for fast high-quality rendering of complex images. All objects are reduced to common world-space geometric entities called micropolygons, and all of the shading and visibility calculations operate on these micropolygons. Each type of calculation is performed in a coordinate system that is ... more

Paper (PDF)


Stochastic Sampling in Computer Graphics

Robert L. Cook
January 1986

Ray tracing, ray casting, and other forms of point sampling are important techniques in computer graphics, but their usefulness has been undermined by aliasing artifacts. In this paper it is shown that these artifacts are not an inherent part of point sampling, but a consequence of using regularly spaced ... more

Paper (PDF)


Distributed Ray Tracing

Robert L. Cook, Thomas Porter, Loren Carpenter
July 1984

Ray tracing is one of the most elegant techniques in computer graphics. Many phenomena that are difficult or impossible with other techniques are simple with ray tracing, including shadows, reflections, and refracted light. Ray directions, however, have been determined precisely, and this had limited the capabilities of ray tracing. By ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 1984


Shade Trees

Robert L. Cook
July 1984

Shading is an important part of computer imagery, but shaders have been based on fixed models to which all surfaces must conform. As computer imagery becomes more sophisticated, surfaces have more complex shading characteristics and thus require a less rigid shading model. This paper presents a flexible tree-structured shading model ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 1984.


A Reflectance Model for Computer Graphics

Robert L. Cook, Kenneth E. Torrance
January 1982

A new reflectance model for rendering computer sythesized images is presented. The model accounts for the relative brightness of different materials and light sources in the same scene. It describes the directional distribution of the reflected light and a color shift that occurs as ... more

Paper (PDF)

Published in Transactions on Graphics, Vol. 1, No. 1, January 1982.


Scalable Laplacian Eigenfluids

Qiaodong Cui, Pradeep Sen, Theodore Kim
August 2018

The Laplacian Eigenfunction method for fluid simulation, which we refer to as Eigenfluids, introduced an elegant new way to capture intricate fluid flows with near-zero viscosity. However, the approach does not scale well, as the memory cost grows prohibitively with the number of eigenfunctions. The method also lacks generality, because ... more

Paper (PDF)

Additional materials: [ScalableEigenFluidMainVideo.mp4], [ScalableEigenFluidSupplementalVideo.mp4], [supplement.pdf]


Subdivision Surfaces in Character Animation

Tony DeRose, Michael Kass, Tien Truong
August 1998

The creation of believable and endearing characters in computer graphics presents a number of technical challenges, including the modeling, animation and rendering of complex shapes such as heads, hands, and clothing. Traditionally, these shapes have been modeled ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 1998.


Compressing Fluid Subspaces

Aaron Demby-Jones, Pradeep Sen, Theodore Kim
May 2016

Subspace fluid simulations, also known as reduced-order simulations, can be extremely fast, but also require basis matrices that consume an enormous amount of memory. Motivated by the extreme sparsity of Laplacian eigenfunctions in the frequency domain, we design a frequency-space codec that is capable of compressing basis matrices by up ... more

Paper (PDF)


Deep Compositing Using Lie Algebras

Tom Duff
July 2017

Deep compositing is an important practical tool in creating digital imagery, but there has been little theoretical analysis of the underlying mathematical operators. Motivated by finding a simple formulation of the merging operation on OpenEXR-style deep images, we show that the Porter-Duff over function is the operator of a Lie group. In its corresponding ... more

Paper (PDF)

To appear in ACM Transactions on Graphics


Building an Orthonormal Basis, Revisited

Tom Duff, James Burgess, Per Christensen, Christophe Hery, Andrew Kensler, Max Liani, Ryusuke Villemin
March 2017

Frisvad [2012b] describes a widely-used computational method for augmenting a given single unit vector with two other vectors to produce an orthonormal frame in three dimensions, a useful operation for any physically based renderer. The implementation has a precision problem: as the z component of the input vector approaches -1, floating point cancellation causes ... more

Paper (PDF)


Better Collisions and Faster Cloth for Pixar's Coco

David Eberle
August 2018

Among the many technical challenges of Pixar's Coco was the need to handle cloth simulation for a densely populated city of skeleton characters. Skeletons posed new challenges to the collision algorithms of our in-house cloth system, Fizt. Continuous collision detection and response is an obvious solution to handling fast motion ... more

Paper (PDF)


Volume Rendering for Pixar's Elemental

Julian Fong
May 2023

This work presents recent updates to volume rendering in RenderMan, the production renderer used at Pixar. With the advent of increasingly complicated volumetric assets such as those seen in Pixar's films Soul and Elemental, our aggregate volume renderer required changes to handle complex water based characters; optimizations for complicated scenes; ... more

Paper (PDF)

SIGGRAPH Talks 2023


Production Volume Rendering

Julian Fong, Magnus Wrenninge, Christopher Kulla, Ralf Habel
July 2017

This course provides an overview of production volume rendering, focused on path tracing. The course will describe practical fundamentals for adding volume rendering to an existing path tracer, cover a complete range of volume integration scenarios and techniques, and describe in detail recent production-proven techniques for optimizing volume rendering.

Paper (PDF)

SIGGRAPH 2017 Course Notes


Simulating Whitewater Rapids in Ratatouille

Eric Froemling, Tolga Goktekin, Darwyn Peachey
May 2007

In Pixar's Ratatouille, a key story point involves a rat being swept through the sewers of Paris, plummeting down waterfalls and along steeply sloping tunnels, through a series of high-speed S- bends which cause the torrent of water to bank up sharply on each turn. Bringing ... more

Paper (PDF)

Available as Pixar Technical Memo #07-03


Elemental Characters: Bringing Water to Life

Max Gilbert, Jacob Kuenzel, Kris Campbell, Greg Gladstone, Jean-Claude Kalache, Fernando de Goes, Jon Barry
May 2023

In Pixar's Elemental, the water characters of Element City are not drenched in water, but made of the element itself. Our goal was to create characters that felt non-human and of water, yet still maintain design, readability and charm. Starting with the concept art (inset) and at every step of ... more

Paper (PDF)

SIGGRAPH Talks 2023


Character Articulation through Profile Curves

Fernando de Goes, William Sheffler, Kurt Fleischer
05 2022

Computer animation relies heavily on rigging setups that articulate character surfaces through a broad range of poses. Although many deformation strategies have been proposed over the years, constructing character rigs is still a cumbersome process that involves repetitive authoring of point weights and corrective sculpts with limited and indirect shaping ... more

Paper (PDF)

Video

Video

SIGGRAPH 2022


Garment Refitting for Digital Characters

Fernando de Goes, Donald Fong, Meredith O'Malley
June 2020

We present a new technique to refit garments between characters of different shapes. Our approach is based on a novel iterative scheme that alternates relaxation and rebinding optimizations. In the relaxation step, we use affine-invariant coordinates in order to adapt the input 3D garment to the shape of a target ... more

Paper (PDF)

Video


Sculpt Processing for Character Rigging

Fernando de Goes, Patrick Coleman, Michael Comet, Alonso Martinez
June 2020

Pose-space sculpting is a key component in character rigging workflows used by digital artists to create shape corrections that fire on top of deformation rigs. However, hand-crafting sculpts one pose at a time is notoriously laborious, involving multiple cleanup passes as well as repetitive manual edits. In this work, we ... more

Paper (PDF)

Video


Discrete Differential Operators on Polygonal Meshes

Fernando de Goes, Andrew Butts, Mathieu Desbrun
April 2020

Geometry processing of surface meshes relies heavily on the discretization of differential operators such as gradient, Laplacian, and covariant derivative. While a variety of discrete operators over triangulated meshes have been developed and used for decades, a similar construction over polygonal meshes remains far less explored despite the prevalence of ... more

Paper (PDF)


Sharp Kelvinlets: Elastic Deformations with Cusps and Localized Falloffs

Fernando de Goes, Doug L. James
July 2019

In this work, we present an extension of the regularized Kelvin-let technique suited to non-smooth, cusp-like edits. Our approach is based on a novel multi-scale convolution scheme that layers Kelvinlet deformations into a finite but spiky solution, thus offering physically based volume sculpting with sharp falloff profiles. We also show ... more

Paper (PDF)

Video

Additional materials: [code.zip]


Mesh Wrap based on Affine-Invariant Coordinates

Fenando de Goes, Alonso Martinez
July 2019

We present a new technique to transfer the mesh connectivity between 3D models of different shapes. In contrast to prior work, our method is designed to wrap meshes under large, locally non-rigid deformations, which are commonly found in feature animations. To achieve this goal, we enrich the traditional iterative closest ... more

Paper (PDF)

Video


Patch-based Surface Relaxation

Fernando de Goes, William Sheffler, Michael Comet, Alonso Martinez, Aimei Kutt
August 2018

From rigging to post-simulation cleanups, surface relaxation is a widely used procedure in feature animation. Over the years, Pixar has experimented with several techniques for this task, mostly based on variants of Laplacian smoothing. Notably, none of existing approaches are suited to reproduce the patch layout of a baseline mesh. ... more

Paper (PDF)


Dynamic Kelvinlets: Secondary Motions based on Fundamental Solutions of Elastodynamics

Fernando de Goes, Doug L. James
May 2018

We introduce Dynamic Kelvinlets, a new analytical technique for real-time physically based animation of virtual elastic materials. Our formulation is based on the dynamic response to time-varying force distributions applied to an infinite elastic medium. The resulting displacements provide the plausibility of volumetric elasticity, the dynamics of compressive and shear ... more

Paper (PDF)

Video

Additional materials: [code.zip], [suppl.zip]

Available as Pixar Technical Memo #18-05


Regularized Kelvinlets: Sculpting Brushes based on Fundamental Solutions of Elasticity

Fernando de Goes, Doug L. James
May 2017

We introduce a new technique for real-time physically based volume sculpting of virtual elastic materials. Our formulation is based on the elastic response to localized force distributions associated with common modeling primitives such as grab, scale, twist, and pinch. The resulting brush-like displacements correspond to the regularization of fundamental solutions ... more

Paper (PDF)

Video: Regularized Kelvinlets

Video: Additional example with ~2M triangles

Additional materials: [gradDerivation.pdf], [multiScaleDerivation.pdf]

SIGGRAPH 2017

Available as Pixar Technical Memo #17-03


Subdivision Exterior Calculus for Geometry Processing

Fernando de Goes, Mathieu Desbrun, Mark Meyer, Tony DeRose
April 2016

This paper introduces a new computational method to solve differential equations on subdivision surfaces. Our approach adapts the numerical framework of Discrete Exterior Calculus (DEC) from the polygonal to the subdivision setting by exploiting the refinability of subdivision basis functions. The resulting Subdivision Exterior Calculus (SEC) provides significant improvements in ... more

Paper (PDF)

Additional materials: [supplemental.pdf], [supplementalFigs.pdf]

SIGGRAPH 2016

Available as Pixar Technical Memo #16-01


Vector Field Processing on Triangle Meshes

Fernando de Goes, Mathieu Desbrun, Yiying Tong
August 2015

While scalar fields on surfaces have been staples of geometry processing, the use of tangent vector fields has steadily grown in geometry processing over the last two decades: they are crucial to encoding directions and sizing on surfaces as commonly required in tasks such as texture synthesis, non-photorealistic rendering, digital ... more

Paper (PDF)

SIGGRAPH Courses 2016, SIGGRAPH Asia Courses 2015


An Effects Recipe for Rolling Dough, Cracking Eggs and Pouring Sauce

Tolga Goktekin, Jon Reisch, Darwyn Peachey, Apurva Shah
May 2007

Creating the digital effects for cooking in Ratatouille posed a number of unique challanges. First we had to adopt efficient methods for simulating a wide variety of material behaviours. Second we needed to direct our simulations in order to match the expressiveness of the character's animation, e.g. forming specific shapes while the character pounds a ... more

Paper (PDF)

Available as Pixar Technical Memo #07-06


Photon Beam Diffusion: A Hybrid Monte Carlo Method for Subsurface Scattering

Ralf Habel, Per H. Christensen, Wojciech Jarosz
June 2013

We present photon beam diffusion, an efficient numerical method for accurately rendering translucent materials. Our approach interprets incident light as a continuous beam of photons inside the material. Numerically integrating diffusion from such extended sources has long been assumed computationally prohibitive, leading to the ubiquitous single-depth dipole approximation and the recent analytic sum-of-Gaussians approach employed ... more

Paper (PDF)

Additional materials: [PBD_matlab_v1.03.zip], [supplemental-theory.pdf]

Published in Computer Graphics Forum (Proceedings of the Eurographics Symposium on Rendering 2013), volume 32, number 4. Eurographics / Blackwell Publishers, June 2013. (Zaragoza, Spain, June 19-21.). Equation 13 amended July 2013.


Subspace Clothing Simulation using Adaptive Bases

Fabian Hahn, Bernhard Thomaszewski, Stelian Coros, Robert W. Sumner, Forrester Cole, Mark Meyer, Tony DeRose, Markus Gross
January 2014

We present a new approach to clothing simulation using low-dimensional linear subspaces with temporally adaptive bases. Our method exploits full-space simulation training data in order to construct a pool of low-dimensional bases distributed across pose space. For this purpose, we interpret the simulation data as offsets from a kinematic deformation ... more

Paper (PDF)

Additional materials: [SubspaceClothingSiggraph2.mp4]

Available as Pixar Technical Memo #14-03


Efficient, Fair Interpolation using Catmull-Clark Surfaces

Mark Halstead, Michael Kass, Tony DeRose
July 1993

We describe an efficient method for constructing a smooth surface that interpolates the vertices of a mesh of arbitrary topological type. Normal vectors can also be interpolated at an arbitrary subset of the vertices. The method improves on existing interpolation techniques in that it is fast, robust and general.

Paper (PDF)

Appeared in SIGGRAPH 1993.


Effective Toon-Style Rendering Control Using Scalar Fields

Alex Harvill
May 2007

An illustration of Gusteau comes to life and introduces a new facet of the film Ratatouille. To do this, a technique was needed to convert an animated 3D character into a 2D illustration. Existing renderman shaders based on normal and depth maps were difficult to control. Post processing per gprim id ... more

Paper (PDF)

Available as Pixar Technical Memo #07-08


Stochastic Generation of (t,s) Sample Sequences

Andrew Helmer, Per Christensen, and Andrew Kensler
Nov 2021

We introduce a novel method to generate sample sequences that are progressively stratified both in high dimensions and in lower-dimensional projections. Our method comes from a new observation that Owen-scrambled quasi-Monte Carlo (QMC) sequences can be generated as stratified samples, merging the QMC construction and random scrambling into a stochastic ... more

Paper (PDF)

Additional materials: [suppl.pdf]

Eurographics Symposium on Rendering 2021


MCQMC 2018 Illumination 101

Christophe Hery
July 2018

We talked at MCQMC 2018 in Rennes (France) about the usage of control variates for direct ligting computation.

Paper (PDF)

MCQMC 2018 Talk Slides


Pixar's Foundation for Materials

Christophe Hery, Ryusuke Villemin, Junyi Ling
August 2017

Though the philosophies and main principles behind our setups date back to our work on Physically Based Lighting for Monsters University, we present the mental models and more modern features and usages covered by PxrSurface and PxrMarschnerHair.

Paper (PDF)

SIGGRAPH 2017 Course Notes


Towards Bidirectional Path Tracing at Pixar

Christophe Hery, Ryusuke Villemin, Florian Hecht
July 2016

On Finding Dory and Piper, we were faced with rendering a lot of water, or creatures and sets seen through water and glass. We worked with production artists to give controls for resolving these difficult light transports. We also learned to cheat these effects where appropriate. In these course notes, ... more

Paper (PDF)


Geometry into Shading

Christophe Hery, Michael Kass, Junyi Ling
October 2014

Sometimes, when 3D CG objects are viewed from a distance, a great deal of geometry can end up inside a single pixel. When this happens, full-sized facets, or pixels in a displacement map should play the role of traditional micro-facets. Here we describe how to alter traditional shading calculations to ... more

Paper (PDF)

Additional materials: [Bump2Roughness.tar.gz]

Available as Pixar Technical Memo #14-04


Physically Based Lighting at Pixar

Christophe Hery, Ryusuke Villemin
July 2013

We recently participated in the Siggraph 2013 Physically Based Shading course, with all notes and documents stored at http://blog.selfshadow.com/publications/s2013-shading-course. We provide here direct access to our own chapter, describing the Physically Based System we designed at Pixar (on top of RenderMan) for the movie Monsters University and the short film ... more

Paper (PDF)


Texture mapping for the Better Dipole model

Christophe Hery
December 2012

We derive an exact diffuse integral for Eugene D"Eon"s new Better Dipole model and we provide the code for numerically inverting it, leading to easy texture mapping for translucency effects.

Paper (PDF)

Available as Pixar Technical Memo #12-11


Importance Sampling of Reflections from Hair Fibers

Christophe Hery, Ravi Ramamoorthi
December 2011

Hair and fur are increasingly important visual features in production rendering, and physically-based light scattering models are now commonly used. In this paper, we enable efficient Monte Carlo rendering of reflections from hair fibers by describing a simple and practical importance sampling strategy for the reflection term in the Marschner hair model. Our ... more

Paper (PDF)

Available as Pixar Technical Memo #11-07


Creating Elemental Characters: From Sparks to Fire

Jonathan Hoffman, Te Hu, Paul Kanyuk, Stephen Marshall, George Nguyen, Hope Schroers, Patrick Witting
May 2023

Pixar has a long history of creating high-quality effects and characters that aid in the telling of wonderful stories. With Disney and Pixar's Elemental, we have taken the next groundbreaking step in creating fully simulated, animated, and stylized characters. In this talk, we will present the framework and process that ... more

Paper (PDF)

SIGGRAPH Talks 2023


Hypertextural Garments on Pixar's Soul

Jonathan Hoffman, Matt Kuruc, Junyi Ling, Alex Marino, George Nguyen, Sasha Ouellet
July 2020

The art direction of Souls version of New York City sought a highly detailed "hypertextural" style to contrast the ethereal volumetric world our characters visit later in the film. The Soul characters team identified that increasing the detail of our garment assets heightened the separation between the two worlds. To ... more

Paper (PDF)


Surface Reconstruction from Unorganized Points

Hugues Hoppe, Tony DeRose, Tom Duchamp, John McDonald, Werner Stuetzle
July 1992

We describe and demonstrate an algorithm that takes as input an unorganized set of points x1,...,xn in R3 on or near an unknown manifold M, and produces as output a simplicial surface that approximates M. Neither the topology, the presence of boundaries, nor the geometry of M are assumed to be known in advance ... more

Paper (PDF)

Published in SIGGRAPH 1992.


Mass Preserving Multi-Scale SPH

Christopher Jon Horvath, Barbara Solenthaler
July 2013

We present a method for performing very high resolution, incompressible fluid simulations at multiple resolutions of detail, simultaneously.

The particle-based method supports user-defined regions of refinement and can handle complex collision boundary conditions while remaining smooth and stable. Conservation of mass in refined detail levels is handled explicitly, overcoming mass-loss ... more

Paper (PDF)

Additional materials: [MultiScaleSPH_PixarTechMemo13.04_July19_2013.mov]

Available as Pixar Technical Memo #13-04


Holding the Shape in Hair Simulation

Hayley Iben, Jacob Brooks, Christopher Bolwyn
July 2019

Hair simulation models are based on physics, but require additional controls to achieve certain looks or art directions. A common simulation control is to use hard or soft constraints on the kinematic points provided by the articulation of the scalp or explicit rigging of the hair [Kaur et al. 2018; ... more

Paper (PDF)

Video


Artistic Simulation of Curly Hair

Hayley Iben, Mark Meyer, Lena Petrovic, Olivier Soares, John Anderson, Andrew Witkin
July 2013

Artistic simulation of hair presents many challenges - ranging from incorporating artistic control to dealing with extreme motions of characters. Additionally, in a production environment, the simulation needs to be fast and results need to be usable "out of the box" (without extensive parameter modifications) in order to produce ... more

Paper (PDF)

Additional materials: [tazVideo-SCA.mov]

Available in the Proceedings of the Symposium on Computer Animation 2013.

Available as Pixar Technical Memo #12-03b

Other versions:


Volume Conserving Finite Element Simulations of Deformable Models

Geoffrey Irving, Craig Schroeder, Ronald Fedkiw
August 2007

We propose a numerical method for modeling highly deformable nonlinear incompressible solids that conserves the volume locally near each node in a finite element mesh. Our method works with arbitrary constitutive models, is applicable to both passive and active materials (e.g. muscles), and works with simple tetrahedra without the need for multiple quadrature points ... more

Paper (PDF)

Available in the proceedings of SIGGRAPH 2007.


Efficient Simulation of Large Bodies of Water by Coupling Two and Three Dimensional Techniques

Geoffrey Irving, Eran Guendelman, Frank Losasso, Ronald Fedkiw
January 2006

We present a new method for the efficient simulation of large bodies of water, especially effective when three-dimensional surface effects are important. Similar to a traditional two-dimensional height field approach, most of the water volume is represented by tall cells which are assumed to have linear pressure profiles. In order to avoid the limitations typically ... more

Paper (PDF)

Additional materials: [movie.avi]

Available in the proceedings of SIGGRAPH 2006


Phong Deformation: A better C0 interpolant for embedded deformation

Doug L. James
July 2020

Physics-based simulations of deforming tetrahedral meshes are widely used to animate detailed embedded geometry. Unfortunately most practitioners still use linear interpolation (or other low-order schemes) on tetrahedra, which can produce undesirable visual artifacts, e.g., faceting and shading artifacts, that necessitate increasing the simulation's spatial resolution and, unfortunately, cost. In this paper, ... more

Paper (PDF)

Video


Orthogonal Array Sampling for Monte Carlo Rendering

Wojciech Jarosz, Afnan Enayet, Andrew Kensler, Charlie Kilpatrick, Per Christensen
July 2019

We generalize N-rooks, jittered, and (correlated) multi-jittered sampling to higher dimensions by importing and improving upon a class of techniques called orthogonal arrays from the statistics literature. Renderers typically combine or "pad" a collection of lower-dimensional (e.g. 2D and 1D) stratified patterns to form higher-dimensional samples for integration. ... more

Paper (PDF)

Additional materials: [images.tar.xz], [supplemental.pdf]


High-Quality Rendering Using Ray Tracing and Photon Mapping

Henrik Wann Jensen, Per H. Christensen
August 2007

Detailed descriptions of the ray-tracing and photon-mapping algorithms for rendering complex scenes with indirect illumination, caustics, participating media, and subsurface scattering. The emphasis is on the practical insight necessary to use and implement these algorithms in production of high-quality image in movies, games, architecture, etc.

Paper (PDF)

Available as Siggraph 2007 course notes, Course Number 8


Harmonic Coordinates for Character Articulation

Pushkar Joshi, Mark Meyer, Tony DeRose, Brian Green, Tom Sanocki
May 2007

In this paper we consider the problem of creating and controlling volume deformations used to articulate characters for use in high-end applications such as computer generated feature films. We introduce a method we call harmonic coordinates that significantly improves upon existing volume deformation techniques. Our deformations are controlled using a topologically flexible structure, called a cage, ... more

Paper (PDF)

Additional materials: [HarmonicCoordinates.divx], [SiggraphSlides.pdf]

Available in the proceedings of Siggraph 2007.

Available as Pixar Technical Memo #06-02b

Other versions:


Singed Silhouettes and Feed Forward Flames: Volumetric Neural Style Transfer for Expressive Fire Simulation

Paul Kanyuk, Vinicius C. Azevedo, Raphael Ortiz, Jingwei Tang
May 2023

While controlling simulated gaseous volumes remains an ongoing battle when seeking realism in computer graphics, creating appealing characters entirely out of these simulations brought this challenge to an entirely new level in Pixar's film Elemental. For fire characters, like the protagonist Ember, their faces and bodies needed to look and ... more

Paper (PDF)

SIGGRAPH Talks 2023


Coherent Noise for Non-Photorealistic Rendering

Michael Kass, Davide Pesare
July 2011

A wide variety of non-photorealistic rendering techniques make use of random variation in the placement or appearance of primitives. In order to avoid the "shower-door" effect, this random variation should move with the objects in the scene. Here we present coherent noise tailored to this purpose. We compute the coherent ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 2011


Smoothed Local Histogram Filters

Michael Kass, Justin Solomon
May 2010

Local image histograms contain a great deal of information useful for applications in computer graphics, computer vision and computational photography. Making use of that information has been challenging because of the expense of computing histogram properties over large neighborhoods. Efficient algorithms exist for some specific computations like the bilateral filter, but not others. ... more

Paper (PDF)

To appear in the Proceedings of SIGGRAPH 2010

Available as Pixar Technical Memo #10-02


Animating Oscillatory Motion With Overlap: Wiggly Splines

Michael Kass, John Anderson
June 2008

Oscillatory motion is ubiquitous in computer graphics, yet existing animation techniques are ill-suited to its authoring. We introduce a new type of spline for this purpose, known as a ``Wiggly Spline.'' The spline generalizes traditional piecewise cubics when its resonance and damping are set to zero, but creates oscillatory animation when its resonance and damping ... more

Paper (PDF)

Available in SIGGRAPH 2008

Available as Pixar Technical Memo #06-06a

Other versions:


Interactive Depth of Field

Michael Kass, Aaron Lefohn, John Owens
January 2006

Accurate computation of depth-of-field effects in computer graphics rendering is generally very time consuming, creating a problematic workflow for film authoring. The computation is particularly challenging because it depends on large-scale spatially-varying filtering that must accurately respect complex boundaries. Here we introduce an approximate depth-of-field computation that is good enough for film preview, yet ... more

Paper (PDF)

Additional materials: [movie.avi]

Available as Pixar Technical Memo #06-01


Robust Skin Simulation in Incredibles 2

Ryan Kautzman, Gordon Cameron, Theodore Kim
August 2018

Robustly simulating the dynamics of skin sliding over a character's body is an ongoing challenge. Skin can become non-physically "snagged" in curved or creased regions, such as armpits, and create unusable results. These problems usually arise when it becomes ambiguous which kinematic surface the skin should be sliding along. We ... more

Paper (PDF)


Correlated Multi-Jittered Sampling

Andrew Kensler
March 2013

We present a new technique for generating sets of stratified samples on the unit square. Though based on jittering, this method is competitive with low-discrepancy quasi-Monte Carlo sequences while avoiding some of the structured artifacts to which they are prone. An efficient implementation is provided that allows repeatable, ... more

Paper (PDF)

Available as Pixar Technical Memo #13-01


Dynamic Deformables: Implementation and Production Practicalities

Theodore Kim, David Eberle
July 2020

Simulating dynamic deformation has been an integral component of Pixar's storytelling since Boo's shirt in Monsters, Inc. (2001). Recently, several key transformations have been applied to Pixar's core simulator Fizt that improve its speed, robustness, and generality. Starting with Coco (2017), improved collision detection and response were incorporated into the ... more

Paper (PDF)

Video

Additional materials: [code.zip]


Anisotropic Elasticity for Inversion-Safety and Element Rehabilitation

Theodore Kim, Fernando de Goes, Hayley Iben
July 2019

We present an analysis of anisotropic hyperelasticity, specifically transverse isotropy, that obtains closed-form expressions for the eigendecompositions of many common energies. We then use these to build fast and concise Newton implementations. We leverage our analysis in two separate applications. First, we show that existing anisotropic energies are not inversion-safe, ... more

Paper (PDF)

Video

Additional materials: [Anisotropy2019_supplement.pdf], [matlab.zip]


Proton: Multitouch Gestures as Regular Expressions

Kenrick Kin, Bjoern Hartmann, Tony DeRose, Maneesh Agrawala
January 2012

Current multitouch frameworks require application developers to write recognition code for custom gestures; this code is split across multiple event-handling callbacks. As the number of custom gestures grows it becomes increasingly difficult to 1) know if new gestures will conflict with existing gestures, and 2) know how to extend existing ... more

Paper (PDF)

To appear in CHI 2012

Available as Pixar Technical Memo #12-02


Eden: A Professional Multitouch Tool for Constructing Virtual Organic Environments

Kenrick Kin, Tom Miller, Bjoern Bollensdorff, Tony DeRose, Bjoern Hartmann, Maneesh Agrawala
January 2011

Set construction is the process of selecting and positioning virtual geometric objects to create a virtual environment used in a computer-animated film. Set construction artists often have a clear mental image of the set composition, but find it tedious to build their intended sets with current mouse and keyboard interfaces. We investigate whether multitouch input can ... more

Paper (PDF)

To appear in the proceedings of SIGCHI 2011

Available as Pixar Technical Memo #11-04


Determining the Benefits of Direct-Touch, Bimanual, and Multifinger Input on a Multitouch Workstation

Kenrick Kin, Maneesh Agrawala, Tony DeRose
May 2009

Multitouch workstations support direct-touch, bimanual, and multifinger interaction. Previous studies have separately examined the benefits of these three interaction attributes over mouse-based interactions. In contrast, we present an empirical user study that considers these three interaction attributes together for a single task, such that we can quantify and compare the performances of each attribute. In our ... more

Paper (PDF)

To appear in Graphics Interface 2009


Dinosaur Input Device

Brian Knep, Craig Hayes, Rick Sayre, Tom Williams
June 1995

We present a system for animating an articulate figure using a physical skeleton, or armature, connected to a workstation. The skeleton is covered with sensors that monitor the orientations of the joints and send this information to the computer via custom-built hardware. ... more

Paper (PDF)

Appeared in the Proceedings of SIGCHI 1995


Articulating the Appeal

Sonoko Konishi, Michael Venturini
May 2007

It's difficult. In our society, rodents are usual portrayed in a negative manner. To overcome this, every department on Ratatouille strove to create appeal. In this sketch we will focus on how this was achieved through articulation.

Paper (PDF)

Available as Pixar Technical Memo #07-12


Elemental Characters: Making Characters Out of Thin Air

Markus Kranzler, Krzysztof Rost, Ravindra Dwivedi, Athena Xenakis, Andrew Pettit
May 2023

Pixar's upcoming feature film Elemental required many new technical solutions due to its ambitious visual language and storytelling. The film's characters, made of different elements - fire, water, air, and earth, required a unique approach in finding answers. For our main Air characters we had to come up with a ... more

Paper (PDF)

SIGGRAPH Talks 2023


From Procedural Panda-monium to Fast Vectorized Execution using PCF Crowd Primitives

Aaron Lo, Venkateswaran Krishna, J.D. Northrup, Mark Hessler, Arnold Moon, Michael Lorenzen, Jonah Laird, and Paul Kanyuk
May 2022

In animation and VFX, crowds are too often considered an "edge case", to be handled by specialized pipeline outside the main workflows. Requirements of scale and traditional reliance on history based simulation have been obstacles to properly building crowd systems into the core functionality of digital content creation software. Pixar's ... more

Paper (PDF)

Siggraph Talk 2022


Deep Shadow Maps

Tom Lokovic, Eric Veach
August 2000

We introduce deep shadow maps, a technique that produces fast, high-quality shadows for primitives such as hair, fur, and smoke. Unlike traditional shadow maps, which store a single depth at each pixel, deep shadow maps store a representation of the fractional visibility through a pixel at all possible depths. Deep ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 2000.


Eyes Without a Face: Integrating detached facial features into Pixar's character pipeline

Anna-Christine Lykkegaard, Ana Lacaze, Jonathan Page
May 2023

From an asset creation perspective, Pixar's first long formseries, Win or Lose, had a daunting number of featured characters. In addition to the large scope of the project, the design pushed further into the stylistic trend of somerecent Pixar films - favoring graphic shape language infacial expressions. The methodology that ... more

Paper (PDF)

SIGGRAPH Talks 2023


Tracking Character Diversity in the Animation Pipeline

Mara MacMahon, Emily Wilson, Peter Nye, Gordon Cameron, Jessica Heidt, Joshua Minor, and Paul Kanyuk
May 2022

As we explore a broad range of characters and stories in our films, it has become increasingly valuable to view breakdowns of our character pools and selections by demographic: to build and use our assets efficiently, reinforce storytelling and world building choices, and ensure consistent decision-making across the pipeline. With the ... more

Paper (PDF)

Siggraph Talk 2022


Key Point Subspace Acceleration and Soft Caching

Mark Meyer, John Anderson
May 2007

Many applications in Computer Graphics contain computationally expensive calculations. These calculations are often performed at many points to produce a full solution, even though the subspace of reasonable solutions may be of a relatively low dimension. The calculation of facial articulation and rendering of scenes with global illumination are two example applications that ... more

Paper (PDF)

Additional materials: [SiggraphSlides.pdf], [softCaching.mov]

Available in the proceedings of Siggraph 2007

Available as Pixar Technical Memo #06-04b

Other versions:


Statistical Acceleration for Animated Global Illumination

Mark Meyer, John Anderson
January 2006

Global illumination provides important visual cues to an animation, however its computational expense limits its use in practice. In this paper, we present an easy to implement technique for accelerating the computation of indirect illumination for an animated sequence using stochastic ray tracing. We begin by computing a quick but noisy solution using a ... more

Paper (PDF)

Additional materials: [ShotRender.mov]

To appear in SIGGRAPH 2006

Available as Pixar Technical Memo #06-03


Hair Emoting with Style Guides in Turning Red

Brandon Montell, Fernando de Goes, Jacob Brooks
May 2022

For Pixar's feature film Turning Red, the grooming and simulation teams faced the challenge of handling characters with millions of fur and hair curves, which often needed to behave differently in each shot reflecting the characters' emotional states. This work describes new tools developed to assist artists in managing and ... more

Paper (PDF)

Siggraph Talk 2022


Elemental Characters: The Living Vegetation of Element City

Greg Mourino, Kris Campbell, Brennan Mitchell, Grace Gilbert
May 2023

The Earth characters of Pixar's Elemental feature a wide range of foliage adornments, ranging from bushes and small plants to trees that tower over their bodies. Creating appealing motion for each of the variations of these characters presented a unique challenge to the Simulation Team, and led to a significant ... more

Paper (PDF)

SIGGRAPH Talks 2023


Creating a Planet and Clouds Lightyears Away

Laura Murphy, Joshua Jenny, Michael O'Brien, Colin Thompson
May 2022

For Lightyear, Space Ranger Buzz Lightyear's exploits take him on a journey around the planet, T'Kani Prime and its neighboring star. In order to create realistic planets as seen from his star ship, we built a new workflow for creating procedural planet terrains and volumetric clouds as seen from space. ... more

Paper (PDF)

Siggraph Talk 2022


Shaping the Elements: Curvenet Animation Controls in Pixar's Elemental

Duc Nguyen, Jeremie Talbot, William Sheffler, Mark Hessler, Kurt Fleischer, Fernando de Goes
May 2023

We present a new shaping rig for authoring layers of animation control that facilitate surface editing in shot work. Our approach expands the curvenet rigging technology [de Goes et al. 2022] by introducing new tools that auto-generate a surface-aligned direct manipulator per curvenet knot. As a result, we obtain a ... more

Paper (PDF)

SIGGRAPH Talks 2023


Feature Adaptive GPU Rendering of Catmull-Clark Subdivision Surfaces

Matthias Niessner, Charles Loop, Mark Meyer, Tony DeRose
January 2012

We present a novel method for high-performance GPU-based rendering of Catmull-Clark subdivision surfaces. Unlike previous methods, our algorithm computes the true limit surface up to machine precision, and is capable of rendering surfaces that conform to the full RenderMan specification for Catmull-Clark surfaces. Specifically, our algorithm can accommodate base meshes ... more

Paper (PDF)

Available in ACM Transactions on Graphics, January 2012.


Space Rangers with Cornrows

Sofya Ogunseitan
June 2022

This presentation is a debrief of the processes and methods added to Pixar's groom pipeline to create the hairstyles of Lightyear characters Alisha and Izzy Hawthorne. The processes include novel ways of generating braids, curls, braid partitioning hairs (edge hairs), and graphic shapes populated with hair.

Paper (PDF)


Everybody's an Effect: Scalable Volumetric Crowds on Elemental

Sasha Ouellet, Aksel Taylan, Arnold Moon, Paul Kanyuk, William Reeves
May 2023

Crowd animation and rendering is challenging enough with hard surface models, but the world of Elemental takes this to a new level by immersing the viewer in a teeming metropolis populated by sentient air, fire, and water, in the form of volumetric characters. By building a new Houdini-Engine character pipeline ... more

Paper (PDF)

SIGGRAPH Talks 2023


Rasterizing Volumes and Surfaces for Crowds on Soul

Sasha Ouellet, Daniel Garcia, Stephen Gustafson, Matt Kuruc, Michael Lorenzen, George Nguyen, Grace Gilbert
July 2020

In order to produce shots with hundreds of multi-volume crowd characters for Soul, we developed a pipeline rooted in rasterization techniques to pose density fields and other shading signals entirely at render-time.

Paper (PDF)


Art-Directed Surface Tearing Simulation

Leon Jeong Wook Park
January 2019

A key sequence in Pixar's Cars 3 includes dramatic surface tearing effects on Lightning McQueen's new body suit. Controlling and stylizing physically-based simulation is one of the hardest topics in CGI productions. To achieve our director's specific vision, we developed an art-directable surface tearing simulation framework. This talk presents our ... more

Paper (PDF)

Available as Pixar Technical Memo #19-01


Texture On Demand

Darwyn Peachey
January 1990

Texture On Demand (TOD) is a technique for organizing large amounts of stored texture data in disk files and accessing it efficiently. Simply reading entire texture images into memory is not a good solution for real memory systems or for virtual memory systems. Texture data should be read from disk files only on ... more

Paper (PDF)

Available as Pixar Technical Memo #217


A Data-Driven Light Scattering Model for Hair

Leonid Pekelis, Christophe Hery, Ryusuke Villemin, Junyi Ling
May 2015

We present an implementation of the [Marschner et al. 2003] model for importance sampling light reflected from hair. The implemen- tation makes use of a version of Adaptive Importance Sampling (AIS), specialized to fit easily sampled distributions to BCSDFs. Our model is novel among importance sampling implementations in that it ... more

Paper (PDF)

Additional materials: [hairlock_eccentricity_085.mov], [hairlock_eccentricity_100.mov]

Available as Pixar Technical Memo #15-02


A statistical framework for comparing importance sampling methods, and an application to rectangular lights

Leonid Pekelis, Christophe Hery
February 2014

Importance sampling methods for ray tracing are numerous. One reason is due to the lack of a robust, quantitative method for comparison. This tech memo takes strides to provide a framework for comparing sampling methods on fair ground. We define a simple, mathematical notion of strictly preferring one method to ... more

Paper (PDF)

Available as Pixar Technical Memo #14-01


Lpics: a Hybrid Hardware-Accelerated Relighting Engine for Computer Cinematography

Fabio Pellacini, Kiril Vidimce, Aaron Lefohn, Alex Mohr, Mark Leone, John Warren
August 2005

In computer cinematography, the process of lighting design involves placing and configuring lights to define the visual appearance of environments and to enhance story elements. This process is labor intensive and time consuming, primarily because ... more

Paper (PDF)

Additional materials: [lpics_siggraph.mp4]

Available in the Proceedings of SIGGRAPH 2005


Volumetric Methods for Simulation and Rendering of Hair

Lena Petrovic, Mark Henne, John Anderson
January 2005

Hair is one of the crucial elements in representing believable digital humans. It is one of the most challenging elements, too, due to the large number of hairs on a human head, their length, and their complex interactions. Hair appearance, in rendering and simulation, is ... more

Paper (PDF)

Additional materials: [clip1.mp4], [clip2.mp4], [clip3.mp4], [clip4.mp4], [clip5.mp4], [clip6.mp4]

Available as Pixar Technical Memo #06-08


Compositing Digital Images

Thomas Porter, Tom Duff
July 1984

Most computer graphics pictures have been computed all at once, so that the rendering program takes care of all computations relating to the overlap of objects. There are several applications, however, where elements must be rendered separately, relying on compositing techniques for the anti-aliased accumulation of the full image. This ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 1984.


FaceBaker: Baking Character Facial Rigs with Machine Learning

Sarah Radzihovsky, Fernando de Goes, Mark Meyer
June 2020

Character rigs are procedural systems that deform a character's shape driven by a set of rig-control variables. Film quality character rigs are highly complex and therefore computationally expensive and slow to evaluate. We present a machine learning method for approximating facial mesh deformations which reduces rig computations, increases longevity of ... more

Paper (PDF)

Video


Advanced Issues in Level of Detail

Martin Reddy
August 2002

Siggraph 2002 course slides. See the abstracts in the additional materials below for more details.

Paper (PDF)

Additional materials: [1-perception-abstract.txt], [2-perception.pdf], [3-terrain-abstract.txt], [4-terrain.pdf]


Rendering Antialiased Shadows with Depth Maps

William T. Reeves, David H. Salesin, Robert L. Cook
July 1987

We present a solution to the aliasing problem for shadow algorithms that use depth maps. The solution is based on a new filtering technique called percentage closer filtering. In addition to antialiasing, the improved algorithm provides soft shadow boundaries that resemble penumbrae. We describe ... more

Paper (PDF)

Available in the Proceedings of SIGGRAPH 1987.


Large Scale Geometric Visibility Culling on Brave

Zachary Repasky, Patrick Schork, Kevin McNamara, Susan Fong
August 2013

Disney/Pixar's Brave is visually complex, containing fully clothed and articulated crowds characters, a forest full of vegetation, ruins littered with debris, and a full fledged castle. In fact, it is so complex that our previous methods to remove unnecessary geometry are no longer adequate in keeping the renders feasible.

On ... more

Paper (PDF)

Additional materials: [visibilityCullingOnBrave.mov]

Available as Pixar Technical Memo #13-05


Engine-eering a Procedural Pipeline with USD

Michael Rice, Joshua Jenny, Will Harrower
May 2023

Typical cache-based non-procedural methods can have downsides within a production studio. Modifications to pre-cached data can introduce an expensive feedback loop between departments (e.g. Layout pushing work back to FX). Proceduralism solves this by allowing artists themselves to make their own modifications, without need for a new cache delivery from ... more

Paper (PDF)

SIGGRAPH Talks 2023


Mio: Fast Multipass Partitioning via Priority-Based Instruction Scheduling

Andrew Riffel, Aaron Lefohn, Kiril Vidimce, Mark Leone, John Owens
August 2004

Real-time graphics hardware continues to offer improved resources for programmable vertex and fragment shaders. However, shader programmers continue to write shaders that require more resources than are available in the hardware. One way to virtualize the resources necessary to run complex shaders is to partition the ... more

Paper (PDF)

Available in the Proceedings of Graphics Hardware 2004


500 Million and Counting: Hair Rendering on Ratatouille

David Ryu
May 2007

Featuring plush rats, well-groomed humans, and a colony of rodents numbering a thousand strong, Ratatouille had shots where the original scene descriptions contained many hundreds of millions of hairs. To make these shots renderable, we developed many new technologies to optimize our RenderMan-based hair rendering pipeline, including caching to speed up runtime sculpting, a technique ... more

Paper (PDF)

Available as Pixar Technical Memo #07-09


Rivers of Rodents: An Animation-Centric Crowds Pipeline for Ratatouille

David Ryu, Paul Kanyuk
May 2007

One of the major technical challenges in the animated film Ratatouille was creating a believable rat colony. In numbers as high as a thousand, these rats participated in highly complex and coordinated behaviors ranging from chaotic swarming to gourmet cooking. Often, the colony was ... more

Paper (PDF)

Available as Pixar Technical Memo #07-02


Example-based Turbulence Style Transfer

Syuhei Sato, Yoshinori Dobashi, Theodore Kim, Tomoyuki Nishita
August 2018

Generating realistic fluid simulations remains computationally expensive, and animators can expend enormous effort trying to achieve a desired motion. To reduce such costs, several methods have been developed in which high-resolution turbulence is synthesized as a post process. Since global motion can then be obtained using a fast, low-resolution simulation, ... more

Paper (PDF)

Additional materials: [FluidStyleTransfer.mp4], [FluidStyleTransfer_Supplemental.mp4]


Fast, Soft Reflections Using Radiance Caches

Apurva Shah, Justin Ritter, Chris King, Stefan Gronsky
May 2007

In Pixar's Ratatouille a lot of scenes take place inside the kitchen where reflective surfaces like counter tops, stoves, pots and pans abound. Furthermore, these surfaces were often burnished or covered with dents, scratches or other displacements, which meant that the reflections were soft and fuzzy. Physically accurate reflections are most ... more

Paper (PDF)

Available as Pixar Technical Memo #07-04


Tone Mapping High Dynamic Range Videos using Wavelets

Qi Shan, Mark Meyer, Tony DeRose, John Anderson
January 2012

We propose a novel 3D wavelet based tone mapping framework for high dynamic range videos. Still image tone mapping methods can be applied to videos in a frame by frame fashion, but they often exhibit haloing artifacts and do not guarantee temporal coherence, resulting in flickering. Directly extending wavelet analysis/synthesis ... more

Paper (PDF)

Available as Pixar Technical Memo #12-01


Extracting and Parametrizing Temporally Coherent Surfaces from Particles

Chen Shen, Apurva Shah
May 2007

From pouring sauces to sudsy sink water to violent sewer rapids, realistic animation of fluids presented interesting challenges in Ratatouille. The various fluid effects were simulated either using a physically-based solver or directly with generic particle systems. Although the simulated particles move as a whole like a fluid, the number ... more

Paper (PDF)

Available as Pixar Technical Memo #07-05


Analytic Eigensystems for Isotropic Distortion Energies

Breannan Smith, Fernando de Goes, Theodore Kim
September 2018

Many strategies exist for optimizing non-linear distortion energies in geometry and physics applications, but devising an approach that achieves the convergence promised by Newton-type methods remains challenging. In order to guarantee the positive semi-definiteness required by these methods, a numerical eigendecomposition or approximate regularization is usually needed. In this paper, ... more

Paper (PDF)

Additional materials: [Matlab.zip], [movie.mov], [supplement.pdf]


Stable Neo-Hookean Flesh Simulation

Breannan Smith, Fernando de Goes, Theodore Kim
December 2017

Non-linear hyperelastic energies play a key role in capturing the fleshy appearance of virtual characters. Real-world, volume-preserving biological tissues have Poisson's ratios near 1/2, but numerical simulation within this regime is notoriously challenging. In order to robustly capture these visual characteristics, we present a novel version of Neo-Hookean elasticity. Our ... more

Paper (PDF)

Video

Additional materials: [snh_code.tar.bz2], [stable_neo_hookean_supplement.pdf]

Errata: The expression for alpha on the last line of Page 4 contained a typo that we have fixed.


Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains

Justin Solomon, Fernando de Goes, Gabriel Peyre, Marco Cuturi, Adrian Butscher, Andy Nguyen, Tao Du, Leonidas Guibas
August 2015

This paper introduces a new class of algorithms for optimization problems involving optimal transportation over geometric domains. Our main contribution is to show that optimal transportation can be made tractable over large domains used in graphics, such as images and triangle meshes, improving performance by orders of magnitude compared to ... more

Paper (PDF)

SIGGRAPH 2015


Caustic Connection Strategies for Bidirectional Path Tracing

Sebastien Speierer, Christophe Hery, Ryusuke Villemin, Wenzel Jakob
March 2018

We propose a new type of sampling strategy for connection-based path tracing algorithms such as bidirectional path tracing. Classical bidirectional path tracing generally exhibits poor performance when sampling light paths involving specular transport (e.g. refraction through dielectrics). We therefore introduce specialized connection strategies that connect through chains of specular events. ... more

Paper (PDF)

Available as Pixar Technical Memo #18-01


Eulerian Solid-Fluid Coupling

Yun Teng, David I.W. Levin, Theodore Kim
December 2016

We present a new method that achieves a two-way coupling between deformable solids and an incompressible fluid where the underlying geometric representation is entirely Eulerian. Using the recently developed Eulerian Solids approach [Levin et al. 2011], we are able to simulate multiple solids undergoing complex, frictional contact while simultaneously interacting ... more

Paper (PDF)


Subspace Condensation: Full Space Adaptivity for Subspace Deformations

Yun Teng, Mark Meyer, Tony DeRose, Theodore Kim
May 2015

Subspace deformable body simulations can be very fast, but can behave unrealistically when behaviors outside the prescribed subspace, such as novel external collisions, are encountered. We address this limitation by presenting a fast, flexible new method that allows full space computation to be activated in the neighborhood of novel events ... more

Paper (PDF)

Additional materials: [paper_0089.mov]

To appear in SIGGRAPH 2015.

Available as Pixar Technical Memo #15-03


Deep Learned Super Resolution for Feature Film Production

Vaibhav Vavilala, Mark Meyer
June 2020

Upscaling techniques are commonly used to create high resolution images, which are cost-prohibitive or even impossible to produce otherwise. In recent years, deep learning methods have improved the detail and sharpness of upscaled images over traditional algorithms. Here we discuss the motivation and challenges of bringing deep learned super resolution ... more

Paper (PDF)


Light Pruning on Toy Story 4

Vaibhav Vavilala
July 2019

Pixar films have recently seen drastically rising light counts via procedural generation, resulting in longer render times and slower interactive workflows. Here we present a fully automated, scalable, and error-free light pruning pipeline deployed on Toy Story 4 that reduces final render times by 15-50% in challenging cases, accelerates interactive ... more

Paper (PDF)


Procedural Techniques for Large, Dynamic Sets in Elemental

Aylwin Villanueva, Mike Ravella, Brandon Montell, Ting Zhang, Hosuk Chang
May 2023

The world of Pixar's film Elemental is inhabited by characters made of fire, water, air and earth, and we needed to give these characters a home that was just as dynamic as they were. Specifically, we needed to build a city with new and distinct forms of architecture for each ... more

Paper (PDF)

SIGGRAPH Talks 2023


Art and Technology at Pixar (SIGGRAPH Asia 2018 Course)

Ryusuke Villemin, Chia-Chi Hu, Sonoko Konishi, Hiroaki Narita, Magnus Wrenninge, David Yu
December 2018

As described by this now famous quote "The art challenges technology, and the technology inspires art", technology has always played an important part in Pixar's movie making process. This course will show how we develop and utilize new technical advancements to tell more appealing stories, using real-world examples from our latest movie Incredibles ... more

Paper (PDF)

SIGGRAPH Asia 2018 Course


Efficient Unbiased Rendering of Thin Participating Media

Ryusuke Villemin, Magnus Wrenninge, Julian Fong
September 2018

In recent years, path tracing has become the dominant image synthesis technique for production rendering. Unbiased methods for volume intergration have followed, and techniques such as delta tracking, ratio tracking and spectral decomposition tracking are all in active use, and this paper is focused on optimizing the underlying mechanics ... more

Paper (PDF)


Importance Resampling for BSSRDF

Ryusuke Villemin, Christophe Hery, Per Christensen
November 2016

We present a method to improve BSSRDF rendering, which reduces variance due to sampling of the scattering exit point. By using importance resampling, we are able to sample any arbitrary diffusion model, taking into account the geometry of the object at the same time. The new method is trivial to implement ... more

Paper (PDF)

Available as Pixar Technical Memo #16-05


Art and Technology at Pixar, from Toy Story to Today

Ryusuke Villemin, Christophe Hery, Sonoko Konishi, Takahito Tejima, David Yu
November 2015

Technology has always played an important part in Pixar's movie making process, starting with Toy Story over 20 years ago. This course will take you on a journey through that technical evolution, focusing on how story drove our technical designs and how we utilized new technical advancements to tell more appealing stories. Finally ... more

Paper (PDF)

SIGGRAPH Asia 2015 Course Notes.


Multiple Importance Sampling for Emissive Effects

Ryusuke Villemin, Christophe Hery
January 2013

We present a method for creating and sampling volumetric light sources directly using the volumetric data, obtaining high quality results with any mirror, glossy or diffuse objects, and integrating with any global illumination framework.

Paper (PDF)

Additional materials: [volumeCornell.mov], [volumeMIS.mov]

Published version available as http://jcgt.org/published/0002/02/10/

Available as Pixar Technical Memo #13-02


Porting RSL to C++

Ryusuke Villemin, Christophe Hery
November 2012

In a modern renderer, relying on recursive ray-tracing, the number of shader calls increases by one or two order of magnitude compared to a straighforward rasterizer dealing only with camera visible objects. Recognizing the potential overhead of RSL parsing in all these shader calls, this report evaluates different C++ pre-compiled ... more

Paper (PDF)

Available as Pixar Technical Memo #12-08


Denoising with Kernel Prediction and Asymmetric Loss Functions

Thijs Vogels, Fabrice Rouselle, Brian McWilliams, Gerhard Roethlin, Alex Harvill, David Adler, Mark Meyer, Jan Novak
May 2018

We present a modular convolutional architecture for denoising rendered images. We expand on the capabilities of kernel-predicting networks by combining them with a number of task-specific modules, and optimizing the assembly using an asymmetric loss. The source aware encoder - the first module in the assembly - extracts ... more

Paper (PDF)


Revamping the Cloth Tailoring Pipeline at Pixar

Christine Waggoner, Fernando de Goes
May 2022

This work presents the most recent updates to the cloth tailoring pipeline at Pixar. We start by reviewing the evolution of cloth authoring tools used at Pixar from 2001 to the present day. Motivated by previous approaches, we introduce a structured workflow for cloth tailoring that manages multiple mesh versions ... more

Paper (PDF)

Siggraph Talk 2022


Virtual Tailoring for Ratatouille: Clothing the Fattest Man in the World

Christine Waggoner, David Baraff
May 2007

He's fat. Enormously so. Essentially a clothed sphere. (A very deformable and complexly animated sphere, with legs, arms, and no neck.) For Ratatouille, creating dynamic costumes for every human character in the film required extensive development and innovation in Pixar's cloth pipeline, particularly for the character Gusteau. Modeling and shepherding ... more

Paper (PDF)

Available as Pixar Technical Memo #07-07


Multithreading for Visual Effects

Martin Watt, Erwin Coumans, George ElKoura, Ronald Henderson, Manuel Kraemer, Jeff Lait, James Reinders
August 2014

In this book, developers from the visual effects industry, including George ElKoura and Manuel Kraemer from Pixar, provide practical advice on multithreading techniques used in popular visual effects software. Concrete examples show how multithreading paradigms are applied to achieve high performance computation for visual effects in the challenging world ... more

Paper (PDF)


CurveCrafter: A System for Animated Curve Manipulation

Nora S Willett, Kurt Fleischer, Haldean Brown, Ilene L E, Mark Meyer
September 2023

Linework on 3D animated characters is an important aspect of stylized looks for films. We present CurveCrafter, a system allowing animators to create new lines on 3D models and to edit the shape and opacity of silhouette curves. Our tools allow users to draw, re-draw, erase, edit and retime user ... more

Paper (PDF)

UIST


Stylizing Ribbons: Computing Surface Contours with Temporally Coherent Orientations

Nora S Willett, Fernando de Goes, Kurt Fleischer, Mark Meyer, Chris Burrows
September 2023

Line work is a core element for the stylization of computer animations used by recent shows. However, existing stylization tech- niques are limited to edge treatments based on brush strokes or textures applied solely on top of curves. In this work, we propose new stylization effects by offering artists direct ... more

Paper (PDF)

IEEE Transactions on Visualization and Computer Graphics


Clean Cloth Inputs: Removing Character Self-Intersections With Volume Simulation

Audrey Wong, David Eberle, Theodore Kim
August 2018

Simulation artists frequently work with characters that self-intersect. When these characters are sent as inputs to a cloth simulator, the results can often contain terrible artifacts that must be addressed by tediously sculpting either the input characters or the output cloth. In this talk, we apply volume simulation to character ... more

Paper (PDF)


Product Importance Sampling of the Volume Rendering Equation using Virtual Density Segments

Magnus Wrenninge, Ryusuke Villemin
January 2020

We propose a new volumetric integration method that combines guiding of candidate point positions and importance resampling. We refer to this as the virtual density segment method (VDS). In particular, we show that this control can be driven by treating invertible PDFs as virtual density sources, which in turn ... more

Paper (PDF)

Available as Pixar Technical Memo #20-01


Path Traced Subsurface Scattering using Anisotropic Phase Functions and Non-Exponential Free Flights

Magnus Wrenninge, Ryusuke Villemin, Christophe Hery
July 2017

With the recent move to path tracing for both surface and volume rendering, subsurface scattering has been one of the last light transport modes to rely on empirical or approximate models. Although rendering of subsurface scattering using path tracing is conceptually simple, making the model artist friendly is not. Our new ... more

Paper (PDF)

Additional materials: [PTSSSAlbedoInversionCoeffs.txt]

Available as Pixar Technical Memo #17-07


Denoising Production Volumetric Rendering

Shilin Zhu, Xianyao Zhang, Gerhard Rothlin, Marios Papas, Mark Meyer
May 2023

Denoising is an integral part of production rendering pipelines that use Monte-Carlo (MC) path tracing. Machine learning based denoisers have been proven to effectively remove the residual noise and produce a clean image. However, denoising volumetric rendering remains a problem due to the lack of useful features and large-scale volume ... more

Paper (PDF)

SIGGRAPH Talks 2023


Site last built: Mon Sep 25 12:13:43 2023