People

Thomas Müller

Thomas is a principal research scientist at NVIDIA working on the intersection of machine learning and (inverse) light transport simulation. His research won multiple best paper awards, was featured in TIME's best inventions of 2022, and is used in movie production, commercial 3D reconstruction and gaming. As part of his research, Thomas created and actively maintains several widely used open source frameworks, including the neural graphics- and 3D-reconstruction tool instant-ngp, the high-speed machine learning framework tiny-cuda-nn, and the image comparison tool tev. Thomas holds a PhD from ETH Zürich & Disney Research and, in a past life, also developed large components of the online rhythm game "osu!".

A list of publications and projects is available on his personal website.

Research Area(s)
Algorithms and Numerical Methods
Artificial Intelligence and Machine Learning
Computer Graphics
Computer Vision
Real-Time Rendering
Main Field of Interest
Artificial Intelligence and Machine Learning
Google Scholar
https://scholar.google.ch/citations?user=csrnbFYAAAAJ&hl=en

Publications

2023

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
Bowen Wen, Jonathan Tremblay, Valts Blukis, Stephen Tyree, Thomas Müller, Alex Evans, Dieter Fox, Jan Kautz, Stan Birchfield
CVPR 2023
Neuralangelo: High-Fidelity Neural Surface Reconstruction
Max Zhaoshuo Li, Thomas Müller, Alex Evans, Russell H. Taylor, Mathias Unberath, Ming-Yu Liu, Chen-Hsuan Lin
CVPR 2023
The Best Inventions of 2023, TIME Magazine
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
Yunzhi Lin, Thomas Müller, Jonathan Tremblay, Bowen Wen, Stephen Tyree, Alex Evans, Patricio A. Vela, Stan Birchfield
ICRA 2023
Recursive Control Variates for Inverse Rendering
Baptiste Nicolet, Fabrice Rousselle, Jan Novák, Alexander Keller, Wenzel Jakob, Thomas Müller
SIGGRAPH 2023

2022

Variable Bitrate Neural Fields
Towaki Takikawa, Alex Evans, Jonathan Tremblay, Thomas Müller, Morgan McGuire, Alec Jacobson, Sanja Fidler
ACM SIGGRAPH 2022 Conference Proceedings
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Thomas Müller, Alex Evans, Christoph Schied, Alex Keller
ACM Transactions on Graphics (SIGGRAPH 2022)
Best Technical Paper, SIGGRAPH 2022, THE BEST INVENTIONS OF 2022, TIME
Unbiased Inverse Volume Rendering With Differential Trackers
Merlin Nimier-David, Thomas Müller, Alex Keller, Wenzel Jakob
ACM Transactions on Graphics (SIGGRAPH 2022)
RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis
Jonathan Tremblay, Moustafa Meshry, Stan Birchfield, Alex Evans, Jan Kautz, Alex Keller, Sameh Khamis, Charles Loop, Nate Morrical, Thomas Müller, Koki Nagano, Towaki Takikawa, Stan Birchfield
ECCV 2022 Workshop on Learning to Generate 3D Shapes and Scenes

2021

Path Guiding Using Spatio-Directional Mixture Models
Ana Dodik, Marios Papas, Cengiz Öztireli, Thomas Müller
Computer Graphics Forum
Dynamic Diffuse Global Illumination Resampling
Zander Majercik, Thomas Müller, Alex Keller, Derek Nowrouzezahrai, Morgan McGuire
Computer Graphics Forum
Extracting Triangular 3D Models, Materials, and Lighting From Images
Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas Müller, Sanja Fidler
CVPR 2022 (Oral)
Real-time Neural Radiance Caching for Path Tracing
Thomas Müller, Fabrice Rousselle, Jan Novák, Alex Keller
ACM Transactions on Graphics

2020

Neural Control Variates
Thomas Müller, Fabrice Rousselle, Alex Keller, Jan Novák
ACM Transactions on Graphics (SIGGRAPH Asia)
Practical Product Sampling by Fitting and Composing Warps
David Hart, Matt Pharr, Thomas Müller, Ward Lopes, Morgan McGuire, Peter Shirley
EuroGraphics Symposium on Rendering