RegFormer：一种用于大规模点云配准的高效投影感知Transformer网络
RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration
AI总结：
本文提出端到端Transformer网络RegFormer，通过投影感知分层Transformer和双射关联Transformer实现大规模点云配准，无需后处理，在KITTI和NuScenes上兼顾精度与效率。
摘要：
尽管点云配准在物体级和室内场景中已取得显著进展，但大规模配准方法却很少被探索。挑战主要来自室外LiDAR扫描的巨大点数量、复杂分布和离群点。此外，大多数现有配准工作通常采用两阶段范式：它们首先通过提取具有判别力的局部特征来寻找对应关系，然后利用估计器（如RANSAC）过滤离群点，这些方法高度依赖精心设计的描述子和后处理选择。为了解决这些问题，我们提出了一种端到端的Transformer网络（RegFormer），用于大规模点云对齐，无需任何进一步的后处理。具体来说，提出了一种投影感知的分层Transformer，通过全局提取点特征来捕获长程依赖并过滤离群点。我们的Transformer具有线性复杂度，即使对于大规模场景也能保证高效率。此外，为了有效减少误匹配，设计了一种双射关联Transformer用于回归初始变换。在KITTI和NuScenes数据集上的大量实验表明，我们的RegFormer在精度和效率方面均取得了具有竞争力的性能。
英文摘要：
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale registration methods are rarely explored. Challenges mainly arise from the huge point number, complex distribution, and outliers of outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local features and then leverage estimators (eg. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment without any further post-processing. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes. Furthermore, to effectively reduce mismatches, a bijective association transformer is designed for regressing the initial transformation. Extensive experiments on KITTI and NuScenes datasets demonstrate that our RegFormer achieves competitive performance in terms of both accuracy and efficiency.
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。
