Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance
Published in IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2024
Overview
Research on improving point cloud completion tasks through novel loss function design.
Key Contributions
- Proposed a novel chamfer distance loss function (based on Landau distribution) for point cloud completion task
- Achieved new state-of-the-art results on some benchmark datasets
© 2026 Jack (Haoying) Zhou. Website built and customized by Jack (Haoying) Zhou from the academicpages template. Please let me know if you notice any glitches.