期刊
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
卷 -, 期 -, 页码 5533-5543出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00546
关键词
-
资金
- Centre for Perceptual and Interactive Intelligence Limited
- General Research Fund through the Research Grants Council of Hong Kong [14204021, 14207319, 14203118, 14208619]
- Research Impact Fund [R5001-18]
- CUHK Strategic Fund
The study proposes a novel framework to enhance the completeness of point cloud by learning a unified and structured latent space. A series of constraints are adopted to promote the learning of such a structured space, with experiments showing that the method outperforms state-of-the-art unsupervised methods on multiple datasets.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据