Christopher Choy
Stanford University, Nvidia (United States), Nvidia (United Kingdom), Stanford Health Care
Papers
6
Total Citations
291
H-Index
5
About
Christopher Choy is a pioneering researcher at the intersection of 3D computer vision, deep learning, and robotics, with a particular focus on sparse and spatiotemporal representation of 3D data. His most influential contribution, "4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks" (2019, 124 citations), introduced a groundbreaking framework for processing 3D video data through four-dimensional convolutions, moving beyond frame-by-frame analysis to enable richer spatiotemporal understanding of LiDAR scans and depth image sequences — a critical advancement for robotics and AR/VR systems. Building on this foundation, his work on Generative Sparse Detection Networks (2020, 115 citations) tackled the inherent sparsity of 3D point clouds to enable efficient single-shot object detection, directly addressing real-world challenges in augmented reality and autonomous systems. Choy has also contributed to terrain reconstruction for mobile robot locomotion in urban environments and deformable object manipulation, demonstrating the breadth of his applied robotics research. His early work on DeformNet further showcased his interest in 3D shape reconstruction from single images. Across his career, Choy has consistently pushed the boundaries of how machines perceive and interact with the three-dimensional world.
Research Focus
Key Achievements
Top Papers
- 14D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks124 citations · 2019
- 2Generative Sparse Detection Networks for 3D Single-Shot Object Detection115 citations · 2020
- 3Neural Scene Representation for Locomotion on Structured Terrain35 citations · 2022
- 4Generative Sparse Detection Networks for 3D Single-shot Object Detection6 citations · 2020
- 5Robotics: Science and Systems XVIII6 citations · 2022
- 6