CRA-PCN：基于层级内与层级间交叉分辨率Transformer的点云补全
CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers
AI总结：
提出Cross-Resolution Transformer进行层级内与层级间交叉分辨率聚合，构建由粗到细的CRA-PCN模型，在多个基准上大幅提升点云补全性能。
摘要：
点云补全是恢复完整点云不可或缺的任务，因为遮挡和有限的传感器分辨率等会导致点云不完整。由粗到细的生成架构系列近期在点云补全中取得巨大成功并逐渐成为主流。在本研究中，我们揭示了这些方法背后的关键要素之一：精心设计的具有显式交叉分辨率聚合的特征提取操作。我们提出了Cross-Resolution Transformer，利用局部注意力机制高效执行交叉分辨率聚合。借助递归设计，所提操作能比常见聚合操作捕获更多尺度的特征，有利于捕获精细几何特征。尽管先前方法已探索了层级间交叉分辨率聚合的各种形式，但层级内聚合及其组合的有效性尚未被分析。通过统一设计，Cross-Resolution Transformer能通过切换输入执行层级内或层级间的交叉分辨率聚合。我们将两种形式的Cross-Resolution Transformer集成到一个上采样块用于点生成，并遵循由粗到细的方式，构建CRA-PCN以通过堆叠的上采样块逐步预测完整形状。大量实验表明，我们的方法在多个广泛使用的基准上大幅优于现有最先进方法。代码可在https://github.com/EasyRy/CRA-PCN获取。
英文摘要：
Point cloud completion is an indispensable task for recovering complete point clouds due to incompleteness caused by occlusion, limited sensor resolution, etc. The family of coarse-to-fine generation architectures has recently exhibited great success in point cloud completion and gradually became mainstream. In this work, we unveil one of the key ingredients behind these methods: meticulously devised feature extraction operations with explicit cross-resolution aggregation. We present Cross-Resolution Transformer that efficiently performs cross-resolution aggregation with local attention mechanisms. With the help of our recursive designs, the proposed operation can capture more scales of features than common aggregation operations, which is beneficial for capturing fine geometric characteristics. While prior methodologies have ventured into various manifestations of inter-level cross-resolution aggregation, the effectiveness of intra-level one and their combination has not been analyzed. With unified designs, Cross-Resolution Transformer can perform intra- or inter-level cross-resolution aggregation by switching inputs. We integrate two forms of Cross-Resolution Transformers into one up-sampling block for point generation, and following the coarse-to-fine manner, we construct CRA-PCN to incrementally predict complete shapes with stacked up-sampling blocks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin on several widely used benchmarks. Codes are available at https://github.com/EasyRy/CRA-PCN.
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。
