Unleash The Power of Color for Point Cloud Registration
Keywords: colored point cloud registration
Abstract: Point cloud registration (PCR) has been an important research subject for many years but remains an open problem, presenting numerous challenges. The stability of existing registration methods is often inadequate, particularly in scenarios with low overlap. This issue primarily arises from the insufficient distinctiveness of extracted point cloud features, leading to ambiguous matches and the proliferation of outliers. To address these bottlenecks in point cloud registration, it is crucial to fully leverage the color information of the point clouds to discern point correspondences effectively.
However, excessive control over color may disrupt the spatial structure of the point cloud, making it essential to find a balance between the aggressiveness and stability of color integration.
To tackle these challenges, we propose UPC-PCR, which unlocks the potential of color information while maintaining stability. Specifically, we design a Curvature-Color Fusion Module (CCF) to initialize distinctive features. Additionally, to balance color aggressiveness, we enhance the geometric structure by introducing a Centroid Angular (CA) embedding for superpoint structure encoding, which is particularly effective in low-overlap scenes.
While CCF and CA ensure the distinctiveness of point features, the aggressive use of color in the feature enhancement process may still introduce errors. Therefore, we develop a robust estimator equipped with Feature-based Compatibility Hypergraph Convolution (FCH) to learn higher-order compatibility of correspondences and effectively filter out outliers.
Evaluation across multiple datasets has demonstrated the state-of-the-art performance of UPC-PCR, achieving registration recalls of 98.4%/90.4% on Color3DMatch/Color3DLoMatch.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4814
Loading