RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
This addresses the challenge of accurate 3D point cloud alignment for applications like robotics and computer vision, though it builds incrementally on diffusion-based techniques.
The paper tackles the problem of point cloud registration by proposing a zero-shot method that refines existing algorithms without requiring training data, achieving significantly improved registration accuracy across diverse datasets.
Recent research leveraging large-scale pretrained diffusion models has demonstrated the potential of using diffusion features to establish semantic correspondences in images. Inspired by advancements in diffusion-based techniques, we propose a novel zero-shot method for refining point cloud registration algorithms. Our approach leverages correspondences derived from depth images to enhance point feature representations, eliminating the need for a dedicated training dataset. Specifically, we first project the point cloud into depth maps from multiple perspectives and extract implicit knowledge from a pretrained diffusion network as depth diffusion features. These features are then integrated with geometric features obtained from existing methods to establish more accurate correspondences between point clouds. By leveraging these refined correspondences, our approach achieves significantly improved registration accuracy. Extensive experiments demonstrate that our method not only enhances the performance of existing point cloud registration techniques but also exhibits robust generalization capabilities across diverse datasets. Codes are available at https://github.com/zhengcy-lambo/RARE.git.