Zhengyang Shen

University of North Carolina at Chapel Hill

Papers

Total Citations

H-Index

About

Zhengyang Shen is a researcher whose work sits at the intersection of geometric deep learning and shape analysis, with a particular focus on point cloud registration and optimal transport. His most-cited paper, "Accurate Point Cloud Registration with Robust Optimal Transport" (2021, 26 citations), introduces a novel framework that leverages robust optimal transport (OT) solvers to significantly improve the accuracy of both optimization-based and deep learning methods for aligning 3D point clouds. This contribution addresses a fundamental challenge in computer vision and robotics—how to match shapes efficiently without sacrificing precision—by demonstrating that modern OT techniques can achieve state-of-the-art performance at an affordable computational cost. Shen's work has been influential in advancing the practical application of optimal transport in geometric matching tasks, bridging the gap between theoretical OT advances and real-world registration problems. His research not only enhances the robustness of point cloud alignment but also provides a principled foundation for future work in shape correspondence and 3D scene understanding. With growing recognition in the field, Shen continues to push the boundaries of how mathematical optimization can drive progress in geometric data analysis.