Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Yuval Haitman, Amit Efraim, Joseph M. Francos• 2026

Related benchmarks

TaskDatasetResultRank
Point cloud registration3DLoMatch (low-overlap)--
25
Point cloud registration3DMatch official (test)
Rotation Accuracy @ 5°95.1
10
Point cloud registrationScanNet Hard v1
Rotation Accuracy (5 deg)88.7
6
Point cloud registrationScanNet SuperGlue v1
Rotation Accuracy @ 5 deg89.5
5
3D Point Cloud RegistrationWaymo (val)
Rotation Accuracy (1°)61.8
4
Point cloud registrationScanNet (Original)
Rotation Accuracy (5 deg)99.4
3
Point cloud registrationLoWaymo (low-overlap)
RRE (deg)4.95
2
Showing 7 of 7 rows

Other info

GitHub

Follow for update