Generative Point Cloud Registration
By: Haobo Jiang , Jin Xie , Jian Yang and more
Potential Business Impact:
Helps 3D scans match up better.
In this paper, we propose a novel 3D registration paradigm, Generative Point Cloud Registration, which bridges advanced 2D generative models with 3D matching tasks to enhance registration performance. Our key idea is to generate cross-view consistent image pairs that are well-aligned with the source and target point clouds, enabling geometry-color feature fusion to facilitate robust matching. To ensure high-quality matching, the generated image pair should feature both 2D-3D geometric consistency and cross-view texture consistency. To achieve this, we introduce Match-ControlNet, a matching-specific, controllable 2D generative model. Specifically, it leverages the depth-conditioned generation capability of ControlNet to produce images that are geometrically aligned with depth maps derived from point clouds, ensuring 2D-3D geometric consistency. Additionally, by incorporating a coupled conditional denoising scheme and coupled prompt guidance, Match-ControlNet further promotes cross-view feature interaction, guiding texture consistency generation. Our generative 3D registration paradigm is general and could be seamlessly integrated into various registration methods to enhance their performance. Extensive experiments on 3DMatch and ScanNet datasets verify the effectiveness of our approach.
Similar Papers
Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
CV and Pattern Recognition
Makes 3D scans match perfectly, even with bad data.
ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance
CV and Pattern Recognition
Makes 3D scans match perfectly, even with messy data.
Cross3DReg: Towards a Large-scale Real-world Cross-source Point Cloud Registration Benchmark
CV and Pattern Recognition
Aligns 3D scans from different cameras accurately.