Yiquan Fang

Papers

Total Citations

H-Index

About

Yiquan Fang is a computer vision researcher whose work centers on 3D perception, geometric deep learning, and 6D object pose estimation. His most notable contribution is the development of the Geometric Constraint Co-attention Network (GCCN), which innovatively leverages object models—represented as canonical point clouds—as explicit prior knowledge to improve pose estimation accuracy. By introducing a co-attention mechanism that enforces geometric constraints between observed scenes and known object models, Fang’s approach addresses a critical challenge in robotics and augmented reality: precisely aligning objects in 3D space from a single RGB-D image. Though early in his career, his GCCN paper has already garnered 13 citations, signaling its impact on the field. This work stands out for its elegant fusion of attention-based learning with geometric reasoning, offering a practical solution for applications requiring robust object manipulation and scene understanding. Fang’s research bridges the gap between raw sensor data and actionable 3D knowledge, making him a promising voice in the next generation of computer vision researchers focused on real-world spatial intelligence.