C-GenReg：基于多视角一致的几何到图像生成的无训练3D点云配准
C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
AI总结：
C-GenReg通过多视角一致的几何到图像生成，结合概率模态融合，实现无训练的3D点云配准，解决了跨模态、采样差异和环境的泛化问题。
摘要：
我们介绍C-GenReg，一种无训练的3D点云配准框架，利用世界尺度生成先验和面向配准的视觉基础模型（VFMs）的互补优势。当前基于学习的3D点云配准方法在跨传感模态、采样差异和环境方面难以泛化。因此，C-GenReg通过将匹配问题转换到辅助图像域，利用世界基础模型合成多视角一致的RGB表示，从而在不进行微调的情况下保持源和目标视图之间的空间一致性。从生成的视图中，一个预训练用于寻找密集对应关系的VFM提取匹配。由此得到的像素对应关系通过原始深度图提升到3D。为进一步增强鲁棒性，我们引入了“匹配后融合”的概率冷融合方案，将生成RGB分支和原始几何分支的两个独立对应后验相结合。这种融合保留了每个模态的归纳偏差，并提供校准的置信度，而无需额外学习。C-GenReg是零样本且即插即用的：所有模块都是预训练的，并且在不进行微调的情况下运行。在室内（3DMatch、ScanNet）和户外（Waymo）基准上的大量实验表明，C-GenReg在零样本性能和跨域泛化方面表现优异。首次展示了在没有影像数据的现实户外LiDAR数据上成功运行的生成配准框架。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
