Xingyu Chen, Wuqiong Zhao, Xinyu Zhang, Tzu-Mao Li
ACM Transaction on Graphics (Proceedings of SIGGRAPH Asia 2026)
a physically-grounded surfel differentiable rendering model for radio frequency signals using Dirichlet kernels
Haolin Lu, Ishit Mehta, Haodong Li, Yu Fu, Tzu-Mao Li, Ravi Ramamoorthi
SIGGRAPH Asia 2026 (conference track full paper)
guiding inverse rendering optimization using image-space continuation with video generation models
Xuan Tang, Kemeng Huang, Gilbert Bernstein, Minchen Li, Tzu-Mao Li
ACM Transaction on Graphics (Proceedings of SIGGRAPH 2026)
differentiable relational operators make elastic and collision simulation easy to implement from energy definitions
Venkataram Sivaram, Sai Bangaru, Ravi Ramamoorthi, Tzu-Mao Li, Jonathan Ragan-Kelley, Frédo Durand
ACM Transaction on Graphics (Proceedings of SIGGRAPH 2026)
language design for statically enforcing correctness of heterogeneous graphics pipelines
Haolin Lu, Liwen Wu, Zimo Wang, Tzu-Mao Li, Ravi Ramamoorthi
ACM Transaction on Graphics (Proceedings of SIGGRAPH 2026)
numerical integration is just about putting points in the domain and weigh them properly
Bing Xu, Mukund Varma T, Cheng Wang, Tzu-Mao Li, Lifan Wu, Bart Wronski, Ravi Ramamoorthi, Marco Salvi
SIGGRAPH 2026 (conference track full paper)
RenderFormer...but on a point cloud!
Xingyu Chen, Xinyu Zhang, Kai Zheng, Xinmin Fang, Tzu-Mao Li, Chris Xiaoxuan Lu, Zhengxiong Li
MobiCom 2026
discontinuity-aware differentiable ray tracing for radio frequency signals
Trevor Hedstrom, Markus Kettunen, Daqi Lin, Chris Wyman, Tzu-Mao Li
Eurographics 2026
a stochastic formulation of the resampling MIS weight in ReSTIR for reusing from large spatial neighborhoods
Yash Belhe, Ishit Mehta, Wesley Chang, Iliyan Georgiev, Michaél Gharbi, Ravi Ramamoorthi, Tzu-Mao Li
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2025)
Best Paper Award
automatic edge sampling for differentiating arbitrary Slang shaders
Haolin Lu, Yash Belhe, Gurprit Singh, Tzu-Mao Li, Toshiya Hachisuka
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2025)
Best Paper Award Honorable Mention
approximating linear operators using Gaussian mixtures for noise-free closed-form integration
Kaiwen Jiang, Jia-Mu Sun, Zilu Li, Dan Wang, Tzu-Mao Li, Ravi Ramamoorthi
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2025)
differentiable radiosity for Gaussian surfels!
Mustafa Yaldiz, Ishit Mehta, Nithin Raghavan, Andreas Meuleman, Tzu-Mao Li, Ravi Ramamoorthi
SIGGRAPH Asia 2025 (conference track full paper)
accurate closed-form downweighting of Fourier feature encoding for prefiltering neural fields
Trevor Hedstrom, Markus Kettunen, Daqi Lin, Chris Wyman, Tzu-Mao Li
ACM Transactions on Graphics (will be presented at SIGGRAPH 2026)
extending GRIS to handle a large amount of techniques in BDPT, including light tracing
Chi-Jui Ho, Yash Belhe, Steve Rotenberg, Ravi Ramamoorthi, Tzu-Mao Li, Nicholas Antipa
International Conference on Computer Vision 2025
efficient hybrid ray-wave imaging simulation that models diffraction and off-axis aberrations and is differentiable
Haolin Lu, Delio Vicini, Wesley Chang, Tzu-Mao Li
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2025)
Best Paper Award
reducing variance of multiple integrals using a shared set of samples, by reweighting the samples with almost zero overhead!
Wesley Chang, Andrew L. Russell, Stephane Grabli, Matt Jen-Yuan Chiang, Christophe Hery, Doug Roble, Ravi Ramamoorthi, Tzu-Mao Li, and Olivier Maury
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2025)
turning hair strands into a small set of guide strands modified by procedural grooms, 100% neural network free!
Venkataram Sivaram, Ravi Ramamoorthi, Tzu-Mao Li
SIGGRAPH 2025 (conference track full paper)
modeling light sources in rendering by physically simulating glow discharge, a plasma often seen in neon lights
Zimo Wang*, Cheng Wang*, Taiki Yoshino, Sirui Tao, Ziyang Fu, Tzu-Mao Li
*equal contribution
Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Highlight
a loss function based on screened Poisson equation that, when minimized, guarantees convergence to a true distance function
Spandan Madan, Tomotake Sasaki, Hanspeter Pfister, Tzu-Mao Li, Xavier Boix
Transactions on Machine Learning Research, 2025
an empirical study showing that adversarial examples still show up even when they are "in-distribution"
Wesley Chang*, Xuanda Yang*, Yash Belhe*, Ravi Ramamoorthi, Tzu-Mao Li
*equal contribution
SIGGRAPH Asia 2024 (conference track full paper)
edge-aware filtering helps optimization of spatially coherent signals (textures, volumes, meshes, etc)
Ziyang Fu, Yash Belhe, Haolin Lu, Liwen Wu, Bing Xu, Tzu-Mao Li
SIGGRAPH Asia 2024 (conference track full paper)
low-dimensional, deterministic diffusion models are useful for BSDF importance sampling!
Peiyu Xu, Sai Bangaru, Tzu-Mao Li, Shuang Zhao
SIGGRAPH Asia 2024 (conference track full paper)
MCMC methods with clever mutation strategies can scale better with geometric complexity in differentiable rendering
Yun-Hsuan Lien, Ping-Chun Hsieh, Tzu-Mao Li, Yu-Shuen Wang
International Conference on Machine Learning 2024
combining discrete and continuous time RL to expliot first-order information for fitting value functions in offline RL
Haolin Lu, Wesley Chang, Trevor Hedstrom, Tzu-Mao Li
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2024)
a spatial data structure and sampling method for path guiding to efficiently reuse samples across pixels
Chuhao Chen, Yuze He, Tzu-Mao Li
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2024)
recurrent transformer blocks are more effective than pixel blending for denoising MLT rendering
Venkataram Sivaram, Ravi Ramamoorthi, Tzu-Mao Li
SIGGRAPH 2024 (conference track full paper)
representing meshes using patches and coordinate neural networks
Bing Xu, Tzu-Mao Li, Iliyan Georgiev, Trevor Hedstrom, Ravi Ramamoorthi
Computer Graphics Forum (Proceedings of Eurographics Symposium on Rendering 2024)
Best Paper Award
path space importance sampling strategies for rendering the difference between two frames
Jesse Michel, Kevin Mu, Xuanda Yang, Sai Preveen Bangaru, Elias Rojas Collins, Gilbert Bernstein, Jonathan Ragan-Kelley, Michael Carbin, Tzu-Mao Li
Proceedings of the ACM on Programming Languages (OOPSLA 2024)
a distribution theory formalism for differentiating parametric discontinuities in programs, and support of first-order functions with separate compilation
Yash Belhe, Bing Xu, Sai Praveen Bangaru, Ravi Ramamoorthi, Tzu-Mao Li
ACM Transactions on Graphics (presented at SIGGRAPH 2024)
importance sampling real-valued functions by decomposing an integral into single-signed ones with overlapping supports
Andrew Spielberg, Fangcheng Zhong, Konstantinos Rematas, Krishna Murthy Jatavallabhula, Cengiz Oztireli, Tzu-Mao Li, Derek Nowrouzezahrai
Nature Machine Intelligence (2023)
a survey article of differentiable graphics algorithms and their applications in machine learning
Kartik Chandra*, Tony Chen*, Tzu-Mao Li, Jonathan Ragan-Kelley, Josh Tenenbaum
*equal contribution
Neural Information Processing Systems 2023 (Spotlight)
using a bidirectional path tracing like algorithm to infer the goal of an agent from its current state
Yash Belhe, Michaél Gharbi, Matthew Fisher, Iliyan Georgiev, Ravi Ramamoorthi, Tzu-Mao Li
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2023)
a hybrid mesh-neural-network 2D representation that preserves discontinuities when zoomed in
Sai Bangaru, Lifan Wu, Tzu-Mao Li, Jacob Munkberg, Gilbert Bernstein, Jonathan Ragan-Kelley, Frédo Durand, Aaron Lefohn, Yong He
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2023)
Slang meets automatic differentiation
Peiyu Xu, Sai Bangaru, Tzu-Mao Li, Shuang Zhao
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2023)
Best Paper Award
warped area sampling in path space with material-form reparameterization
Liwen Wu*, Rui Zhu*, Mustafa Yaldiz, Yinhao Zhu, Hong Cai, Janarbek Matai, Fatih Porikli, Tzu-Mao Li, Manmohan Chandraker, Ravi Ramamoorthi
*equal contribution
International Conference on Computer Vision 2023 (oral presentation)
irradiance and radiance caching for speeding up and robustifying inverse path tracing, with an emitter estimation heuristic
Wesley Chang, Venkataram Sivaram, Derek Nowrouzezahrai, Toshiya Hachisuka, Ravi Ramamoorthi, and Tzu-Mao Li
SIGGRAPH 2023 (conference track full paper)
making sampling in inverse rendering faster by reusing information in gradient-based optimization
Kartik Chandra, Tzu-Mao Li, Joshua Tenenbaum, Jonathan Ragan-Kelley
SIGGRAPH 2023 (conference track full paper) /
Proceedings of the 45th Annual Conference of the Cognitive Science Society (CogSci 2023)
(There are two versions of this paper. The first paper is written for graphics audience, and the second one is written for cognitive science audience.)
automatically synthesizing stories as animation sequences by optimizing Theory of Mind models
Shiyang Jia, Stephanie Wang, Tzu-Mao Li, Albert Chern
Proceedings of the ACM on Computer Graphics and Interactive Techniques (SCA 2023)
simulating physics in a periodic time domain
Nithin Raghavan*, Yan Xiao*, Kai-En Lin, Tiancheng Sun, Sai Bi, Zexiang Xu, Tzu-Mao Li, Ravi Ramamoorthi
*equal contribution
Computer Graphics Forum (Proceedings of Eurographics Symposium on Rendering 2023)
hybrid neural wavelet precomputed radiance transfer
Tzu-Mao Li
IEEE Computer Graphics and Applications: Dissertation Impact, 2022
summary of the visions of my PhD thesis.
Sai Praveen Bangaru, Michaél Gharbi, Tzu-Mao Li, Fujun Luan, Kalyan Sunkavalli, Miloš Hašan, Sai Bi, Zexiang Xu, Gilbert Bernstein, Frédo Durand
SIGGRAPH Asia 2022 (conference track full paper)
unbiased differentiable SDF rendering. concurrent with Vicini et al.'s work. some extra memory saving tricks are introduced.
Kartik Chandra, Tzu-Mao Li, Joshua Tenenbaum, Jonathan Ragan-Kelley
SIGGRAPH 2022 (conference track full paper)
synthesizing optical illusion by differentiating through Bayesian vision models
Karima Ma, Michael Gharbi, Andrew Adams, Shoaib Kamil, Tzu-Mao Li, Connelly Barnes, Jonathan Ragan-Kelley
ACM Transaction on Graphics (Presented at SIGGRAPH 2022)
systematically exploring the Pareto frontier of efficient and high-quality data-driven image processing algorithms
Luke Anderson, Andrew Adams, Karima Ma, Tzu-Mao Li, Tian Jin, Jonathan Ragan-Kelley
Proceedings of the ACM on Programming Languages (OOPSLA 2021)
a scalable and data-driven Halide autoscheduler that can process large pipelines and output GPU schedules
Yu-Chen Wang, Yu-Ting Wu, Tzu-Mao Li, Yung-Yu Chuang
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2021)
adapting both the clustering and sampling distribution in lightcuts rendering using a data-driven method built on reinforcement lightcuts learning
Yu-Ting Wu, Tzu-Mao Li, I-Chao Shen, Hong-Shiang Lin, Yung-Yu Chuang
High-Performance Graphics (HPG) 2021
fast sampling-based cross bilateral filtering for depth completion with large missing regions
Sai Praveen Bangaru*, Jesse Michel*, Kevin Mu, Gilbert Bernstein, Tzu-Mao Li, Jonathan Ragan-Kelley
*equal contribution
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2021)
a programming language perspective on the automatic differention of integrals with discontinuous integrands, and its applications in physics and rendering
Sai Praveen Bangaru, Tzu-Mao Li, Frédo Durand
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2020)
solving the differentiable rendering boundary integral with standard area sampling in an unbiased way using divergence theorem
Tzu-Mao Li, Michal Lukáč, Michaël Gharbi, Jonathan Ragan-Kelley
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2020)
design choices and applications of differentiable vector graphics rasterization
Shuang Zhao, Wenzel Jakob, Tzu-Mao Li
SIGGRAPH 2020 Course
our differentiable rendering tutorial!
Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, Frédo Durand
International Conference on Learning Representation (ICLR) 2020
automatic differentiated Taichi and applications in model-based reinforcement learning
Yuanming Hu, Tzu-Mao Li, Luke Anderson, Jonathan Ragan-Kelley, Frédo Durand
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2019)
a data-oriented compiler that decouples hierarchical sparse data structures design from computation
Andrew Adams, Karima Ma, Luke Anderson, Riyadh Baghdadi, Tzu-Mao Li, Michaël Gharbi, Benoit Steiner, Steven Johnson, Kayvon Fatahalian, Frédo Durand, Jonathan Ragan-Kelley
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2019)
first Halide autoscheduler that produces faster code comparing to human experts on average
Michaël Gharbi, Tzu-Mao Li, Miika Aittala, Jaakko Lehtinen, Frédo Durand
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2019).
permutation invariant mapping from Monte Carlo samples to an image through splatting
Tzu-Mao Li
MIT PhD Dissertation
ACM SIGGRAPH 2020 Outstanding Doctoral Dissertation Award (announcement)
a coherent view of my PhD research, with some new discussions regarding previous work, and some background reviews
Dejan Azinović, Tzu-Mao Li, Anton Kaplanyan, Matthias Nießner
Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (oral presentation)
applying differentiable rendering for material and lighting reconstruction
Tzu-Mao Li, Miika Aittala, Frédo Durand, Jaakko Lehtinen
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2018)
computing gradients of the light transport equation through an explicit sampling of Dirac delta functions on triangle edges
Tzu-Mao Li, Michaël Gharbi, Andrew Adams, Frédo Durand, Jonathan Ragan-Kelley
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2018)
Halide meets automatic differentiation, and a new way to think about data-driven image processing
Luke Anderson, Tzu-Mao Li, Jaakko Lehtinen, Frédo Durand
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2017)
a programming language for Monte Carlo rendering that automatically computes the probability density of a light path sample
Tzu-Mao Li, Jaakko Lehtinen, Ravi Ramamoorthi, Wenzel Jakob, Frédo Durand
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2015)
a Metropolis light transport algorithm that makes use of automatically differentiated Hessian matrix of light path contribution
Yu-Ting Wu, Tzu-Mao Li, Yu-Hsun Lin, and Yung-Yu Chuang
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2015
subsurface scattering with many-lights using matrix sampling
Tzu-Mao Li, Yu-Ting Wu, Yung-Yu Chuang
ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2012)
Stein's unbiased risk estimator for sampling and denoising in Monte Carlo rendering