面向远距离点云配准的密度不变特征
Density-invariant Features for Distant Point Cloud Registration
AI总结：
本文提出分组对比学习方案GCL，通过构造满足独立同分布条件的正样本组来训练密度不变的全卷积特征提取器，显著提升了远距离LiDAR点云配准在KITTI和nuScenes上的召回率。
摘要：
远距离室外LiDAR点云的配准对于扩展协作式自动驾驶车辆的三维视觉至关重要，但由于重叠区域小以及观测点密度之间存在巨大差异，该任务仍面临挑战。本文提出了一种分组对比学习（Group-wise Contrastive Learning，GCL）方案，用于提取密度不变的几何特征，以配准远距离室外LiDAR点云。我们通过理论分析和实验表明，对比学习中的正样本应当满足独立同分布（i.i.d.）条件，才能训练出密度不变的特征提取器。基于这一结论，我们提出了一种简单而有效的训练方案，迫使同一空间位置上的多个点云（称为正样本组）的特征彼此相似，从而自然避免了由一对点云引入的采样偏差，以符合独立同分布原则。所得到的全卷积特征提取器比现有最先进方法更强大且具有密度不变性，在KITTI和nuScenes基准上将远距离场景的配准召回率分别提高了40.9%和26.9%。代码可在https://github.com/liuQuan98/GCL获取。
英文摘要：
Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area and a huge disparity between observed point densities. In this paper, we propose Group-wise Contrastive Learning (GCL) scheme to extract density-invariant geometric features to register distant outdoor LiDAR point clouds. We mark through theoretical analysis and experiments that, contrastive positives should be independent and identically distributed (i.i.d.), in order to train densityinvariant feature extractors. We propose upon the conclusion a simple yet effective training scheme to force the feature of multiple point clouds in the same spatial location (referred to as positive groups) to be similar, which naturally avoids the sampling bias introduced by a pair of point clouds to conform with the i.i.d. principle. The resulting fully-convolutional feature extractor is more powerful and density-invariant than state-of-the-art methods, improving the registration recall of distant scenarios on KITTI and nuScenes benchmarks by 40.9% and 26.9%, respectively. Code is available at https://github.com/liuQuan98/GCL.
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。
