Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud
Year: 2025
Type: preprint
Abstract: Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitations: Supervised methods heavily rely on ground truth, which limits their generalization to real-world datasets due to the synthetic-to-real domain gap. Unsupervised methods require complete point clouds to compose unpaired training data, and weakly-supervised methods need multi-view observations of the object. Existing self-supervised methods frequently produce unsatisfactory predictions due to the limited capabilities of their self-supervised signals. To overcome these challenges, we propose a novel self-supervised point cloud completion method. We design a set of novel self-supervised signals based on multi-view augmentations of the single partial point cloud. Additionally, to enhance the model's learning ability, we first incorporate Mamba into self-supervised point cloud completion task, encouraging the model to generate point clouds with better quality. Experiments on synthetic and real-world datasets demonstrate that our method achieves state-of-the-art results.
Source: arXiv (Cornell University)
Authors: Lu, Jingjing, Pi, Huilong, Qin, Yunchuan, Tang, Zhuo, Li, Ruihui
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7083843992
Cites:
Cited by:
Related to: