Yuefan Shen

Papers

Total Citations

H-Index

About

Yuefan Shen is a researcher specializing in 3D computer vision and geometric deep learning, with a particular focus on point cloud analysis and domain adaptation. His most recognized work centers on bridging the gap between different geometric representations of 3D data — a critical challenge in deploying machine learning models for real-world applications such as autonomous driving and robotics. Shen's most notable contribution, "Domain Adaptation on Point Clouds via Geometry-Aware Implicits," addresses a fundamental problem in 3D vision: point clouds of the same object can vary dramatically in geometric structure depending on the scanning device or environment, making it difficult for models trained on one domain to generalize to another. His innovative approach leverages geometry-aware implicit representations to reconcile these variations, offering a principled solution to cross-domain generalization in point cloud learning. The work has garnered over 64 citations, underscoring its significance and relevance to the research community. Shen's research sits at a compelling intersection of geometric representation learning and transfer learning, areas of growing importance as 3D sensing technologies become increasingly embedded in autonomous systems. His contributions offer practical pathways for more robust and adaptable 3D perception models in real-world deployments.