Kayvon photo
Associate Professor of Computer Science
Stanford University
Contact Info
Gates Building 366
Our group architects high-performance visual computing systems that enable advanced computer graphics and visual perception applications. Our recent research efforts can be categorized into several themes:
Enabling Efficient Image/Video Processing at Scale. Emerging visual computing applications require efficient analysis and mining of large repositories of visual data (images, videos, RGBD). We are developing a distributed computing support for applications that query, analyze and mine image and video collections at the scale of thousands of cloud CPUs or hundreds of GPUs. See the Scanner website for more detail.
Optimizing Compilers for Accelerated Hardware. We've recently developed techniques for automatically scheduling image processing pipelines onto CPUs/GPUs, and are working on systems that generate specialized hardware implementations for FPGAs or ASICs.
DNN Model Design for Efficient Inference. Since building efficient systems involves both efficient hardware and efficient algorithms, we are exploring DNN designs that achieve higher accuracy per unit cost using techniques such as conditional DNN execution and specialization to video stream contents.
I'm always looking for great students that wish to work on these topics, or bring their own ideas.
I gave an Arch 2030 workshop keynote on how visual computing applications will drive architectual innovation in the year 2030. The talk is on Youtube. An updated version of the slides is here.
Here are a few tips on how to give clear research talks (or class project talks).
What Makes a Graphics Systems Paper Beautiful: This is an article on systems thinking principles that may be helpful to authors or reviewers of graphics systems papers.
Experiences Building Online Events in Ohyay: I've run A LOT of virtual events since the pandemic started (virtual parties, virtual classes, conferences, etc). In collaboration with Ohyay.co, we've built up a lot of know-how about technical and non-technical ways to make virtual events better. I tried to braindump some of those observations here in a Youtube talk to the Stanford HCI group. (If these topics are interesting to you, come talk to me!)
I've written two posts documenting how I created my own virtual classroom toolkit which provides virtual venues for lectures, office hours, small group work, and student socials. The toolkit is built on the ohyay platform, and it is free and completely customizable for your own needs. You are welcome to use it for your own teaching.
I created this talk, Do Grades Matter, to challenge students to think bigger than just striving to get good grades in a bunch of hard classes.
Want to get outside but still sleep in your own bed at night? Try one of my favorite local Bay Area hikes.
Before moving to Stanford, I taught the following courses at CMU.
Graduated students:
Spotting Temporally Precise, Fine-Grained Events in Video
James Hong, Haotian Zhang, Michaël Gharbi, Matthew Fisher, Kayvon Fatahalian
ECCV 2022 (to appear)
Path Tracing of Terabyte-Scale Scenes using Thousands of Cloud CPUs
Sadjad Fouladi, Brennan Shacklett, Fait Poms, Arjun Arora, Alex Ozdemir, Deepti Raghavan, Pat Hanrahan, Kayvon Fatahalian, Keith Winstein
Transactions on Graphics 2022
Low-shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories
Fait Poms*, Vishnu Sarukkai*, Ravi Teja Mullapudi, Nimit S. Sohoni, William R. Mark, Deva Ramanan, Kayvon Fatahalian
ICCV 2021
Learning Rare Category Classifiers on a Tight Labeling Budget
Ravi Teja Mullapudi, Fait Poms, William R. Mark, Deva Ramanan, Kayvon Fatahalian
ICCV 2021
Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition
James Hong, Matthew Fisher, Michaël Gharbi, Kayvon Fatahalian
ICCV 2021
Analysis of Faces in a Decade of US Cable TV News
James Hong, Will Crichton, Haotian Zhang, Daniel Y. Fu, Jacob Ritchie, Jeremy Barenholtz, Ben Hannel, Xinwei Yao, Michaela Murray, Geraldine Moriba, Maneesh Agrawala, Kayvon Fatahalian
KDD 2021
[Visit the Stanford Cable TV Analyzer website for more info.]
Large Batch Simulation for Deep Reinforcement Learning
Brennan Shacklett, Erik Wijmans, Aleksei Petrenko, Manolis Savva, Dhruv Batra, Vladlen Koltun, Kayvon Fatahalian
ICLR 2021
Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players
Haotian Zhang, Cristobal Sciutto, Maneesh Agrawala, Kayvon Fatahalian
Transactions on Graphics 2021
Iterative Text-based Editing of Talking-heads Using Neural Retargeting
Xinwei Yao, Ohad Fried, Kayvon Fatahalian, Maneesh Agrawala
Transactions on Graphics 2021
Background Splitting: Finding Rare Classes in a Sea of Background
Ravi Teja Mullapudi*, Fait Poms*, William R. Mark, Deva Ramanan, Kayvon Fatahalian
CVPR 2021
Analyzing Who and What Appears in a Decade of US Cable TV News
James Hong, Will Crichton, Haotian Zhang, Daniel Y. Fu, Jacob Ritchie, Jeremy Barenholtz, Ben Hannel, Xinwei Yao, Michaela Murray, Geraldine Moriba, Maneesh Agrawala, Kayvon Fatahalian
Paper on arXiv:2008.06007, Aug 2020
[Visit the Stanford Cable TV Analyzer website for more info.]
Design Adjectives: A Framework for Interactive Model-Guided Exploration of Parameterized Design Spaces
Evan Shimizu, Matt Fisher, Sylvain Paris, Jim McCann, Kayvon Fatahalian
UIST 2020
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Daniel Y. Fu*, Mayee F. Chen*, Frederic Sala, Sarah M. Hooper, Kayvon Fatahalian, Christopher Ré
ICML 2020
Aetherling: Type-Directed Scheduling of Streaming Accelerators
David Durst, Matthew Feldman, Dillon Huff, David Akeley, Ross Daly, Gilbert Louis Bernstein, Marco Patrignani, Kayvon Fatahalian, Pat Hanrahan
PLDI 2020
Multi-Resolution Weak Supervision for Sequential Data
Frederic Sala, Paroma Varma, Jason Fries, Daniel Y. Fu, Shiori Sagawa, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James R. Priest, Christopher Ré
NeurIPS 2019
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Daniel Y. Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher Ré, Kayvon Fatahalian
Paper on arXiv:1910.02993, Oct 2019
Online Model Distillation for Efficient Inference
Ravi Mullapudi, Steven Chen, Keyi Zhang, Deva Ramanan, Kayvon Fatahalian
ICCV 2019, code on Github
Learning to Optimize Halide with Tree Search and Random Programs
Andrew Adams, Karima Ma, Luke Anderson, Riyadh Baghdadi, Tzu-Mao Li, Michaël Gharbi, Benoit Steiner, Steven Johnson, Kayvon Fatahalian, Frédo Durand, Jonathan Ragan-Kelley
Finding Layers Using Hover Visualizations
Evan Shimizu, Matt Fisher, Sylvain Paris, Kayvon Fatahalian
Graphics Interface 2019
Exploratory Stage Lighting Design using Visual Objectives
Evan Shimizu, Sylvain Paris, Matt Fisher, Ersin Yumer, Kayvon Fatahalian
Eurographics 2019
Scanner: Efficient Video Analysis at Scale
Alex Poms, William Crichton, Pat Hanrahan, Kayvon Fatahalian
Slang: Language Mechanisms for Building Extensible Real-time Shading Systems
Yong He, Kayvon Fatahalian, Tess Foley
HydraNets: Specialized Dynamic Architectures for Efficient Inference
Ravi Mullapudi, William R. Mark, Noam Shazeer, Kayvon Fatahalian
CVPR 2018
Shader Components: Modular and High Performance Shader Development
Yong He, Tess Foley, Teguh Hofstee, Haomin Long, Kayvon Fatahalian
Automatically Scheduling Halide Image Processing Pipelines
Ravi Teja Mullapudi, Andrew Adams, Dillon Sharlet, Jonathan Ragan-Kelley, Kayvon Fatahalian
A System for Rapid Exploration of Shader Optimization Choices
Yong He, Tess Foley, Kayvon Fatahalian
LED Street Light Research Project Part II: New Findings
Stephen Quick, Donald Carter, Kayvon Fatahalian, Cynthia Limauro
CMU Technical Report, Summer 2016
The Rise of Mobile Visual Computing Systems
Kayvon Fatahalian
IEEE Pervasive Computing, April/June 2016
Automatically Splitting a Two-Stage Lambda Calculus
Nicolas Feltman, Carlo Anguili, Umut A. Acar, Kayvon Fatahalian
European Symposium on Programming (ESOP) 2016
KrishnaCam: Using a Longitudinal, Single-Person, Egocentric Dataset for Scene Understanding Tasks
Krishna Kumar Singh, Kayvon Fatahalian, Alexei Efros
WACV 2016
A System for Rapid, Automatic Shader Level-of-Detail
Yong He, Tess Foley, Natalya Tatarchuk, Kayvon Fatahalian
SIGGRAPH Asia 2015
Aggregate G-Buffer Anti-Aliasing
Cyril Crassin, Morgan McGuire, Kayvon Fatahalian, Aaron Lefohn
I3D 2015
(An updated and extended version of the paper appears in TVCG 2016.)
Extending the Graphics Pipeline with Adaptive, Multi-Rate Shading
Yong He, Yan Gu, Kayvon Fatahalian
Self-Refining Games using Player Analytics
Matt Stanton, Ben Humberston, Brandon Kase, James O'Brien, Kayvon Fatahalian, Adrien Treuille
Near-exhaustive Precomputation of Secondary Cloth Effects
Doyub Kim, Woojong Koh, Rahul Narain, Kayvon Fatahalian, Adrien Treuille, James O'Brien
Efficient BVH Construction via Approximate Agglomerative Clustering
Yan Gu, Yong He, Kayvon Fatahalian, Guy Blelloch
High Performance Graphics 2013
SRDH: Specializing BVH Construction and Traversal Order Using Representative Shadow Ray Sets
Nicolas Feltman, Minjae Lee, Kayvon Fatahalian
High Performance Graphics 2012
Evolving the Real-Time Graphics Pipeline for Micropolygon Rendering
Kayvon Fatahalian, Stanford University Ph.D. Dissertation, 2011
Reducing Shading on GPUs using Quad-Fragment Merging
Kayvon Fatahalian, Solomon Boulos, James Hegarty, Kurt Akeley, William R. Mark, Henry Moreton, Pat Hanrahan
Space-Time Hierarchical Occlusion Culling for Micropolygon Rendering with Motion Blur
Solomon Boulos, Edward Luong, Kayvon Fatahalian, Henry Moreton, Pat Hanrahan
High Performance Graphics 2010
Hardware Implementation of Micropolygon Rasterization with Motion and Defocus Blur
John S. Brunhaver, Kayvon Fatahalian, Pat Hanrahan
High Performance Graphics 2010
A Lazy Object-Space Shading Architecture With Decoupled Sampling
Christopher A. Burns, Kayvon Fatahalian, William R. Mark
High Performance Graphics 2010
DiagSplit: Parallel, Crack-Free, Adaptive Tessellation for Micropolygon Rendering
Matthew Fisher, Kayvon Fatahalian, Solomon Boulos, Kurt Akeley, William R. Mark, Pat Hanrahan
SIGGRAPH Asia 2009
Data-Parallel Rasterization of Micropolygons with Defocus and Motion Blur
Kayvon Fatahalian, Edward Luong, Solomon Boulos, Kurt Akeley, William R. Mark, Pat Hanrahan
High Performance Graphics 2009
GRAMPS: A Programming Model for Graphics Pipelines
Jeremy Sugerman, Kayvon Fatahalian, Solomon Boulos, Kurt Akeley, Pat Hanrahan
Transactions on Graphics (TOG) January 2009
A Closer Look at GPUs
Kayvon Fatahalian and Mike Houston
Communications of the ACM. Vol. 51, No. 10 (October 2008)
(also published as "GPUs: A Closer Look": ACM Queue. March/April. 2008)
A Portable Runtime Interface for Multi-level Memory Hierarchies
Mike Houston, Ji Young Park, Manman Ren, Timothy J. Knight, Kayvon Fatahalian, Alex Aiken, William J. Dally, Pat Hanrahan
PPOPP 2008
Compilation for Explicitly Managed Memory Hierarchies
Timothy J. Knight, Ji Young Park, Manman Ren, Mike Houston, Mattan Erez, Kayvon Fatahalian, Alex Aiken, William J. Dally, Pat Hanrahan
PPOPP 2007
Sequoia: Programming the Memory Hierarchy
Kayvon Fatahalian, Timothy J. Knight, Mike Houston, Mattan Erez, Daniel R Horn, Larkhoon Leem, Ji Young Park, Manman Ren, Alex Aiken, William J. Dally, Pat Hanrahan
Supercomputing 2006
Understanding the Efficiency of GPU Algorithms for Matrix-Matrix Multiplication
Kayvon Fatahalian, Jeremy Sugerman, Pat Hanrahan
Graphics Hardware 2004
Brook for GPUs: Stream Computing on Graphics Hardware
Ian Buck, Tess Foley, Daniel Horn, Jeremy Sugerman, Kayvon Fatahalian, Mike Houston, Pat Hanrahan
Precomputing Interactive Dynamic Deformable Scenes
Doug L. James and Kayvon Fatahalian
Slang GPU Shading Language. Slang is a shading language that extends HLSL with new capabilities for building modular, extensible, and high-performance real-time shading systems. Slang is now the shading language for NVIDIA's Falcor research rendering system. See the Slang website or the SIGGRAPH 2018 paper for more.
Self-Refining Interactive Games (graphics with 100's of machines and a lot of latency)
How do we build platforms that take graphics applications from one user on a single GPU to 10,000 machines and one million users in the cloud? Even though computer graphics has always been at the vanguard of parallel computing, there has been little success using modern cloud-based computing resources to improve interactive experiences. In this project we asked the question, how could we leverage the massive storage and batch processing capabilities of the cloud to generate new forms of interactive worlds -- and we took a "precompute everything" approach to doing so. Since one cannot precompute everything about an complex interactive world, the challenge is to determine what is most important to precompute, so these parts can be presented to the user with the highest-quality graphics. We find that by recording statistics of users playing a game, we can build a model of user behavior, and then concentrate large-scale, cloud-based precomputation of graphics and physics around the states that users are most likely to encounter. The result is a self-refining game whose dynamics improve with play, ultimately providing realistically rendered, rich fluid dynamics in real time on a mobile device. For more detail, see our work applied these ideas to cloth simulation and fluid simulation.
A Real-Time Micropolygon Rendering Pipeline (evolving the GPU pipeline for tiny triangles)
GPUs will soon have the compute horsepower to render scenes containing cinematic-quality surfaces in real-time. Unfortunately, if they render these subpixel polygons (micropolygons) using the same techniques as they do for large triangles today, GPUs will perform extremely inefficiently. Instead of trying to parallelize Pixar's Reyes micropolygon rendering system, we're taking a hard look at how the existing Direct3D 11 rendering pipeline, and GPU hardware implementations, must evolve to render micropolygon workloads efficiently in a high-throughput system. Changes to software interfaces, algorithms, and HW design are fair game! Slides describing what we've learned can be found in this SIGGRAPH course talk or in my dissertation: Evolving the Real-Time Graphics Pipeline for Micropolygon Rendering.
GRAMPS (a framework for heterogeneous parallel programming)
There are two ways to think about GRAMPS. Graphics folks should think of GRAMPS as a system for building custom graphics pipelines. We simply gave up on adding more and more configurable knobs to existing pipelines like OpenGL/Direct3D and instead allow the programmer to programmatically define a custom pipeline with an arbitrary number of stages connected by queues. To non-graphics folks, GRAMPS is a stream programming system that embraces heterogeneity in underlying architecture and anticipates streaming workloads that exhibit both regular and irregular (dynamic) behavior. The GRAMPS runtime dynamically schedules GRAMPS programs onto architectures containing a mixture of compute-optimized cores, generic CPU cores, and fixed-function processing units.
The Sequoia Programming Language ("Programming the Memory Hierarchy")
Sequoia is a hierarchical stream programming language that arose from the observation that expressing locality, not parallelism is the most important responsibility of parallel application programmers in scientific/numerical domains. Sequoia presents a parallel machine as an abstract hierarchy of memories and gives the programmer explicit control over data locality and communication through this hierarchy using first-class language constructs (basically, Sequoia supports nested kernels and streams of streams). Sequoia programs have run on a variety of exposed-communication architectures such as clusters, the CELL processor, GPUs, and even supercomputing clusters at Los Alamos. The best way to learn about Sequoia is to read our SC06 paper.
Brook/Merrimac (stream processing for scientific computing)
I helped out with the BrookGPU (abstracting the GPU as a stream processor for numerical computing) and Merrimac Streaming Supercomputer projects. Brook was the academic precursor to NVIDIA's CUDA.

Our work has been supported by the National Science Foundation (IIS-1253530, IIS-1422767, IIS-1539069) and by INTEL, NVIDIA, QUALCOMM, GOOGLE, ADOBE, FACEBOOK, ACTIVISION, APPLE, AMAZON, THE INTERNET ARCHIVE, and THE BROWN INSTITUTE FOR MEDIA INNOVATION.