Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud

TMLR Paper5035 Authors

Abstract: Unsupervised Domain Adaptation is crucial for point cloud learning due to geometric variations across different generation methods and sensors. To tackle this challenge, we propose Curvature Diversity-Driven Nuclear-Norm Wasserstein Domain Alignment (CDND). We first introduce a Curvature Diversity-driven Deformation Reconstruction (CurvRec) task, enabling the model to extract salient features from semantically rich regions of a given point cloud. We then propose a theoretical framework for Deformation-based Nuclear-norm Wasserstein Discrepancy (D-NWD), extending the Nuclear-norm Wasserstein Discrepancy to original and deformed samples. Our theoretical analysis demonstrates that D-NWD is effective for any deformation method. Empirical experiment results show that our CDND achieves state-of-the-art performance by a noticeable margin over existing approaches.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Mathieu_Salzmann1

Submission Number: 5035