C-GenReg：基于多视图一致几何到图像生成与概率模态融合的免训练三维点云配准
C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
将点云配准转化为图像域匹配问题，利用世界基础模型生成多视图一致RGB，再借助视觉基础模型提取稠密对应，为跨模态配准提供免训练、即插即用的新范式。
原文依据 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).
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 C-GenReg，一种免训练的三维点云配准框架，它利用了世界级生成先验与面向配准的视觉基础模型（VFM）的互补优势。当前基于学习的三维点云配准方法难以在传感模态、采样差异和环境之间泛化。因此，C-GenReg 通过将匹配问题转移到 VFM 擅长的辅助图像域，使用世界基础模型从输入几何合成多视图一致的 RGB 表示，从而增强几何点云配准分支。这种生成式转移在无需任何微调的情况下保持了源视图和目标视图之间的空间一致性。从这些生成的视图中，一个预训练用于寻找稠密对应关系的 VFM 提取匹配。所得的像素对应关系通过原始深度图提升回三维。为了进一步增强鲁棒性，我们引入了一种“先匹配后融合”的概率冷融合方案，该方案结合了两个独立的对应后验，即生成 RGB 分支的后验与原始几何分支的后验。这种有原则的融合保留了每个模态的归纳偏置，并在无需任何额外学习的情况下提供了校准的置信度。C-GenReg 是零样本且即插即用的：所有模块都是预训练的，无需微调即可运行。在室内（3DMatch、ScanNet）和室外（Waymo）基准上的大量实验证明了强大的零样本性能和卓越的跨域泛化能力。我们首次展示了一个生成式配准框架，该框架在图像不可用的真实室外激光雷达数据上成功运行。
英文原文摘要 1707 字符
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's 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 imagery is unavailable.