Principal Research Scientist and Senior Research Manager at NVIDIA
Exploring the intersection of computer vision and robotics
I lead a small group of amazing researchers in computer vision and robotics at NVIDIA, and I teach a class at the University of Washington. Previously, I was at Microsoft and Clemson University. I received my Ph.D. from Stanford University.
RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
RSS '26
Press: NVIDIA blog post
CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
CVPR '26
Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
CVPR '26
FoundationStereo: Zero-Shot Stereo Matching
CVPR '25
Award: CVPR Best Paper Award Candidate
News: #1 on Middlebury Stereo Evaluation - Version 3 (2025/02/03 – 2025/03/04)
News: #1 on ETH3D Low-Res Two-View Benchmark (2024/11/15 – 2025/05/14)
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
CVPR '24
Award: BOP Challenge 2024 "Early Bird" Award
News: #1 on BOP leaderboard for unseen 6D pose estimation (2023/11/19 – 2024/09/03)
I am the author of Image Processing and Analysis (2018), an introductory textbook about the mathematical and algorithmic foundations of image processing and computer vision.
Introduction to Computer Vision (2026) is an updated introductory book (lecture notes) with working Python code, written for my course at the University of Washington.