Chongruo Wu

Shanghai Artificial Intelligence Laboratory

Papers

Total Citations

H-Index

About

Chongruo Wu is a leading researcher in computer vision and machine learning, with a focus on advancing video understanding and segmentation for real-world applications. His work bridges the gap between static image segmentation and dynamic video environments, particularly for robotics and autonomous driving. Wu’s most notable contribution is the development of VideoSAM, a pioneering framework for open-world video segmentation that extends the capabilities of the Segment Anything Model (SAM) to continuous video frames. This innovation enables robust object association and perception across time, addressing critical challenges in autonomous systems. With over 2 citations on this recent 2025 publication alone, Wu’s research is already gaining traction for its practical impact. His achievements include pushing the boundaries of open-world perception, where models must handle unseen objects and dynamic scenes without retraining. Wu’s work is essential reading for students and researchers interested in video segmentation, autonomous driving, and robotic perception, offering a scalable solution for real-time, adaptable vision systems.