Angjoo Kanazawa

Computer Science · Physical Sciences

42h-index15.3kcitations167works5.72yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(62), Advanced Vision and Imaging(56), 3D Shape Modeling and Analysis(44), Computer Graphics and Visualization Techniques(36), Human Motion and Animation(27)

Publications167 total

Human-level 3D shape perception emerges from multi-view learning
arXiv (Cornell University)·2026Open Access
Human-level 3D shape perception emerges from multi-view learning
ArXiv.org·2026Open Access
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
arXiv (Cornell University)·2026Open Access
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
arXiv (Cornell University)·2026Open Access
Flow Policy Gradients for Robot Control
ArXiv.org·2026Open Access
Flow Policy Gradients for Robot Control
arXiv (Cornell University)·2026Open Access
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
ArXiv.org·2026Open Access
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
arXiv (Cornell University)·2026Open Access
Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
ArXiv.org·2025Open Access
Visually Prompted Benchmarks Are Surprisingly Fragile
ArXiv.org·2025Open Access
Visually Prompted Benchmarks Are Surprisingly Fragile
arXiv (Cornell University)·2025Open Access
Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
arXiv (Cornell University)·2025Open Access
PyRoki: A Modular Toolkit for Robot Kinematic Optimization
2025
Cameras as Relative Positional Encoding
arXiv (Cornell University)·2025Open Access
Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
arXiv (Cornell University)·2025Open Access
Segment Any Motion in Videos
2025· 1 cited
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
2025· 9 cited
Continuous 3D Perception Model with Persistent State
2025· 10 cited
Reconstructing People, Places, and Cameras
2025
Estimating Body and Hand Motion in an Ego-sensed World
2025· 3 cited
page 1 of 9Next →

Frequent Co-authors

Jitendra Malik(13), Matthew Tancik(10), Michael J. Black(7), David W. Jacobs(7), Georgios Pavlakos(6), Ruilong Li(5), Pieter Abbeel(5), Sergey Levine(5), Alex Yu(4), Vickie Ye(4), Hao Li(4), Noah Snavely(4), Federica Bogo(3), Christoph Lassner(3), Peter Gehler(3), Evonne Ng(3), Justin Kerr(3), Xue Bin Peng(3), Aleksander Holynski(3), Jathushan Rajasegaran(3)