arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.15580cs.CV
收藏

学习结构化潜在空间实现无监督点云补全

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

The Chinese University of Hong Kong(香港中文大学);Samsung Research Institute China - Beijing (SRC-B)(三星中国研究院-北京(SRC-B))

Yingjie Cai, Kwan-Yee Lin, Chao Zhang, Qiang Wang, Xiaogang Wang, Hongsheng Li

摘要:

无监督点云完备化的目的是以不成对的方式估计部分点云对应的完整点云。这是一个关键但具有挑战性的问题,因为没有配对的部分完全监督,可以直接利用。在这项工作中,我们提出了一个新的框架,它学习一个统一的和结构化的潜在空间,编码部分和完整的点云。具体来说,我们将一系列相关的部分点云映射成多个完整的形状和遮挡代码对,并融合代码以获得它们在统一潜在空间中的表示。为了加强这种结构化的潜在空间的学习,所提出的方法采用了一系列的约束,包括结构化的排名正则化,潜在代码交换约束,以及相关的部分点云的分布监督。通过建立这样一个统一的、结构化的隐空间,可以获得更好的部分完备几何一致性和形状完备精度。大量的实验表明,我们提出的方法在合成ShapeNet和真实世界的KITTI,ScanNet和Matterport3D数据集上的性能始终优于最先进的无监督方法。

英文摘要:

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-complete supervision that can be exploited directly. In this work, we propose a novel framework, which learns a unified and structured latent space that encoding both partial and complete point clouds. Specifically, we map a series of related partial point clouds into multiple complete shape and occlusion code pairs and fuse the codes to obtain their representations in the unified latent space. To enforce the learning of such a structured latent space, the proposed method adopts a series of constraints including structured ranking regularization, latent code swapping constraint, and distribution supervision on the related partial point clouds. By establishing such a unified and structured latent space, better partial-complete geometry consistency and shape completion accuracy can be achieved. Extensive experiments show that our proposed method consistently outperforms state-of-the-art unsupervised methods on both synthetic ShapeNet and real-world KITTI, ScanNet, and Matterport3D datasets.

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。

↑