无承诺的上下文：非刚性变形下的鲁棒稠密对应

中文摘要 AI 辅助

非刚性点云配准旨在为变形的源表面上的每个点找到对应的目标点。点级匹配保留了完整的目标点云，但当不同区域具有相似的局部几何结构时，对应关系会变得模糊。区域方法或从粗到细的方法提供了更广泛的空间上下文，但不正确的区域匹配可能在稠密匹配之前就排除了正确的对应关系。我们提出了CoCo-Reg，它利用区域补丁来丰富稠密点特征，而不允许补丁预测限制最终的点级搜索。CoCo-Reg构建最远点采样补丁，在源和目标之间及内部交换几何信息，使用身份校正的点重叠度监督补丁相似性，并将得到的区域信息投影回稠密点特征。最终的配准阶段仍然在全局点级候选选择之前对整个目标点云进行评分。在跨越九个变形级别的726个保留的ModelNet10对象上，两个已建立的学习型基线获得了0.1993和0.1921的平均对应误差，而CoCo-Reg获得了0.0547。相对于其点级基线，这减少了72.6%。CoCo-Reg在92.3%的成对测试对象上实现了更低的对应误差，并将误差高于0.1的点的平均比例从47.3%降低到17.3%。Chamfer距离和HD95也以相同方向下降，并且CoCo-Reg在所有测试的变形级别上保持更低。这些结果支持在稠密非刚性对应中使用区域上下文，而无需对最终搜索施加硬性的补丁级限制。由于评估使用每种方法的一个检查点，报告的性能提升表征了完整系统，而不是单个组件的孤立因果贡献。代码将公开提供。

英文摘要

Non-rigid point-cloud registration aims to find the corresponding target point for each point on a deforming source surface. Point-level matching keeps the full target cloud available, but correspondence becomes ambiguous when different regions have similar local geometry. Regional or coarse-to-fine methods provide broader spatial context, but an incorrect regional match can exclude the correct correspondence before dense matching. We propose CoCo-Reg, which uses regional patches to enrich dense point features without allowing patch predictions to restrict the final point-level search. CoCo-Reg constructs farthest-point-sampled patches, exchanges geometric information within and between source and target, supervises patch similarity using identity-corrected point overlap, and projects the resulting regional information back to dense point features. The final registration stage still scores the full target cloud before global point-level candidate selection. On 726 held-out ModelNet10 objects across nine deformation levels, two established learning-based baselines obtain mean correspondence errors of 0.1993 and 0.1921, whereas CoCo-Reg obtains 0.0547. Relative to its point-level baseline, this is a 72.6\% reduction. CoCo-Reg achieves lower correspondence error on 92.3\% of paired test objects and reduces the mean fraction of points with error above 0.1 from 47.3\% to 17.3\%. Chamfer distance and HD95 decrease in the same direction, and CoCo-Reg remains lower across all tested deformation levels. These results support using regional context for dense non-rigid correspondence without imposing a hard patch-level restriction on the final search. Because evaluation uses one checkpoint per method, the reported gains characterize the complete systems rather than the isolated causal contribution of an individual component. Code will be made publicly available.

发表机构

• Mannheim Institute for Intelligent Systems in Medicine (MIISM)（曼海姆智能系统医学研究所）
• Medical Faculty Mannheim, Heidelberg University（海德堡大学曼海姆医学院）

机构由 AI 辅助整理，请以论文原文为准。