P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising
This addresses the problem of noise in 3D point clouds for applications like computer vision and robotics, with incremental novelty in adapting an existing bridge method to a new domain.
The paper tackles 3D point cloud denoising by adapting Diffusion Schrödinger bridges to learn an optimal transport plan between paired point clouds, achieving significant improvements over existing methods on datasets like PU-Net, ScanNet++, and ARKitScenes.
In this work, we tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schrödinger bridges to points clouds. Unlike previous approaches that predict point-wise displacements from point features or learned noise distributions, our method learns an optimal transport plan between paired point clouds. Experiments on object datasets like PU-Net and real-world datasets such as ScanNet++ and ARKitScenes show that P2P-Bridge achieves significant improvements over existing methods. While our approach demonstrates strong results using only point coordinates, we also show that incorporating additional features, such as color information or point-wise DINOv2 features, further enhances the performance. Code and pretrained models are available at https://p2p-bridge.github.io.