GeoTransformer：基于几何Transformer的快速鲁棒点云配准
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
AI总结：
本文提出GeoTransformer，通过编码成对距离和三元组角度学习几何特征，实现低重叠场景下无需RANSAC的快速鲁棒点云配准，在3DLoMatch上显著提升内点率和召回率。
摘要：
我们研究点云配准中提取准确对应关系的问题。最近的无关键点方法通过绕过可重复关键点的检测展现出巨大潜力，而可重复关键点的检测尤其在低重叠场景下十分困难。这些方法在下采样的超点上寻找对应关系，然后将对应关系传播到稠密点。超点的匹配基于其相邻块是否重叠。这种稀疏且松散的匹配需要能够捕捉点云几何结构的上下文特征。我们提出Geometric Transformer，简称GeoTransformer，用于学习几何特征以实现鲁棒的超点匹配。它编码成对距离和三元组角度，使其对刚性变换具有不变性，并在低重叠情况下具有鲁棒性。这种简洁的设计获得了惊人的高匹配精度，使得在对齐变换估计中无需RANSAC，从而实现了100倍的加速。在涵盖室内、室外、合成、多路和非刚性场景的丰富基准上的大量实验证明了GeoTransformer的有效性。值得注意的是，在具有挑战性的3DLoMatch基准上，我们的方法将内点率提高了18到31个百分点，并将配准召回率提高了超过7个点。我们的代码和模型可在https://github.com/qinzheng93/GeoTransformer获取。
英文摘要：
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to $100$ times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by $18{\sim}31$ percentage points and the registration recall by over $7$ points on the challenging 3DLoMatch benchmark. Our code and models are available at \url{https://github.com/qinzheng93/GeoTransformer}.
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。
