C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
About
We introduce C-GenReg, a training-free framework for 3D point cloud registration that leverages the complementary strengths of world-scale generative priors and registration-oriented Vision Foundation Models (VFMs). Current learning-based 3D point cloud registration methods struggle to generalize across sensing modalities, sampling differences, and environments. Hence, C-GenReg augments the geometric point cloud registration branch by transferring the matching problem into an auxiliary image domain, where VFMs excel, using a World Foundation Model to synthesize multi-view-consistent RGB representations from the input geometry. This generative transfer, preserves spatial coherence across source and target views without any fine-tuning. From these generated views, a VFM pretrained for finding dense correspondences extracts matches. The resulting pixel correspondences are lifted back to 3D via the original depth maps. To further enhance robustness, we introduce a "Match-then-Fuse" probabilistic cold-fusion scheme that combines two independent correspondence posteriors, that of the generated-RGB branch with that of the raw geometric branch. This principled fusion preserves each modality inductive bias and provides calibrated confidence without any additional learning. C-GenReg is zero-shot and plug-and-play: all modules are pretrained and operate without fine-tuning. Extensive experiments on indoor (3DMatch, ScanNet) and outdoor (Waymo) benchmarks demonstrate strong zero-shot performance and superior cross-domain generalization. For the first time, we demonstrate a generative registration framework that operates successfully on real outdoor LiDAR data, where no imagery data is available.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Point cloud registration | 3DLoMatch (low-overlap) | -- | 25 | |
| Point cloud registration | 3DMatch official (test) | Rotation Accuracy @ 5°95.1 | 10 | |
| Point cloud registration | ScanNet Hard v1 | Rotation Accuracy (5 deg)88.7 | 6 | |
| Point cloud registration | ScanNet SuperGlue v1 | Rotation Accuracy @ 5 deg89.5 | 5 | |
| 3D Point Cloud Registration | Waymo (val) | Rotation Accuracy (1°)61.8 | 4 | |
| Point cloud registration | ScanNet (Original) | Rotation Accuracy (5 deg)99.4 | 3 | |
| Point cloud registration | LoWaymo (low-overlap) | RRE (deg)4.95 | 2 |