MHopReg：面向点云配准的高效层次化多跳图搜索
MHopReg: Efficient Hierarchical Multi-Hop Graph Search for Point Cloud Registration
把对应点筛选建模为兼容图上的层次化多跳搜索，用簇均衡种子采样覆盖低重叠区域的碎片化内点，并用分布感知排序在多个假设中挑空间分布均匀的变换——这套「图搜索+种子采样+假设排序」流程可直接迁移到低重叠点云配准、特征匹配外点剔除等视觉几何任务。
原文依据 we propose a hierarchical multi-hop graph search framework that progressively refines correspondences to address these challenges
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于对应关系的点云配准中的外点剔除在真实场景下面临两个根本性挑战。首先，低重叠区域会产生稀疏且碎片化的内点分布，传统的一步式全局搜索策略难以发现这些内点。其次，大规模场景带来稠密的对应输入，对搜索算法的精度—效率权衡提出了严苛要求。为此，我们提出一种层次化多跳图搜索框架，通过逐步精化对应关系来应对上述挑战。该方法利用变换不变嵌入构建兼容图以预测对应置信度，为簇均衡的种子采样奠定基础，从而确保对碎片化区域的全面覆盖。这些经过策略性选取的种子随后驱动层次化多跳扩展，在多分辨率图层上逐步发现内点，同时规避了穷举式全局搜索的高复杂度。最后，分布感知排序联合评估几何一致性与空间覆盖度，从多个假设中选出分布良好的变换。在 3DMatch、3DLoMatch 和 KITTI 上的实验表明，我们的方法在低重叠与大规模场景下均取得了与现有方法相比极具竞争力的性能。
英文原文摘要 1424 字符
Outlier rejection for correspondence-based point cloud registration confronts two fundamental challenges in real-world scenarios. First, low-overlap regions yield sparse and fragmented inlier distributions that are difficult to discover using conventional one-step global search strategies. Second, large-scale scenes present dense correspondence inputs that impose stringent requirements on the accuracy-efficiency trade-off of search algorithms. To this end, we propose a hierarchical multi-hop graph search framework that progressively refines correspondences to address these challenges. Our method constructs a compatibility graph with transformation-invariant embeddings to predict correspondence confidence, establishing the foundation for cluster-balanced seed sampling that ensures comprehensive coverage across fragmented regions. These strategically selected seeds subsequently drive hierarchical multi-hop expansion, progressively discovering inliers through multi-resolution graph layers while circumventing the high complexity of exhaustive global search. Finally, distribution-aware ranking jointly evaluates geometric consistency and spatial coverage to select well-distributed transformations from multiple hypotheses. Experiments on 3DMatch, 3DLoMatch, and KITTI demonstrate that our method achieves highly competitive performance compared to existing methods in both low-overlap and large-scale scenarios.