arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.03762cs.CV
收藏

基于场景补全的上下文形状先验学习的稀疏单扫描LiDAR点云分割

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);Shanghai University(上海大学)

Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

摘要:

LiDAR点云分析是三维计算机视觉的核心任务,尤其是自动驾驶领域。然而,由于单扫描LiDAR点云的严重稀疏性和噪声干扰,实现精确的语义分割是不平凡的。在本文中,我们提出了一种新的稀疏激光雷达点云语义分割框架辅助学习上下文形状先验。在实践中,单个扫描点云的初始语义分割(SS)可以通过任何吸引人的网络来实现,然后流入语义场景完成(SSC)模块作为输入。通过合并LiDAR序列中的多个帧作为监督,优化的SSC模块已经从序列LiDAR数据中学习了上下文形状先验,完成了从稀疏单扫描点云到密集点云的过程。因此,它通过完全的端到端训练本质上改进了SS优化。此外,提出了一个点-体素交互(PVI)模块,以进一步加强SS和SSC任务之间的知识融合,即,促进点云的不完整局部几何形状和完整的体素全局结构的相互作用。此外,辅助的SSC和PVI模块可以在推理过程中被丢弃,而不会给SS带来额外的负担。大量的实验证实,我们的JS 3C-Net在SemanticKITTI和SemanticPOSS基准测试中都取得了优异的性能,即,4%和3%的改善。

英文摘要:

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

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。

↑