Peirong Liu

University of North Carolina at Chapel Hill

Papers

Total Citations

H-Index

About

Peirong Liu’s research lies at the intersection of geometric deep learning, shape analysis, and optimal transport, with a focus on advancing 3D point cloud registration and motion transfer. His most influential work, “Accurate Point Cloud Registration with Robust Optimal Transport” (2021), has garnered 26 citations and demonstrates how modern optimal transport solvers can significantly enhance both optimization-based and deep learning methods for aligning 3D shapes. By integrating robust OT into registration pipelines, Liu achieved notable accuracy gains at a manageable computational cost, addressing a longstanding challenge in computer vision and robotics. In a related vein, his work on “Self-appearance-aided Differential Evolution for Motion Transfer” (2021) explores unsupervised techniques for animating static images using driving videos, preserving source identity without labeled data. Though early in his career, Liu’s contributions are already shaping how researchers approach geometric correspondence and motion synthesis. His ability to bridge theoretical optimal transport with practical applications marks him as an emerging voice in the field, with potential for lasting impact on autonomous systems, medical imaging, and graphics.