Caelen Wang
Papers
1
Total Citations
9
H-Index
1
About
Caelen Wang is a leading researcher in robotic perception and manipulation, with a focus on bridging the gap between 3D vision and physical interaction. Their key contributions center on learning-based amodal 3D reconstruction, where they pioneered methods that prioritize stability and connectivity over mere visual fidelity—a paradigm shift that enables robots to infer complete object geometries from partial observations. This work, exemplified in their highly cited 2020 paper (9 citations), allows model-based robotic systems to adapt to novel objects in single or few shots, dramatically improving manipulation robustness in unstructured environments. Wang's research addresses a critical bottleneck in robotics: how to make perception systems that understand not just what objects look like, but how they can be physically grasped and manipulated. By redefining reconstruction objectives to include task-relevant properties, they have influenced a growing body of work at the intersection of computer vision and robotics. Their approach has been adopted by laboratories developing next-generation industrial and service robots, demonstrating that perception systems optimized for physical interaction outperform those trained purely on visual metrics.
Research Focus
Key Achievements
Top Papers
- 1