Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918148786094080 |
|---|---|
| author | Lu, Jingjing Pi, Huilong Qin, Yunchuan Tang, Zhuo Li, Ruihui |
| author_facet | Lu, Jingjing Pi, Huilong Qin, Yunchuan Tang, Zhuo Li, Ruihui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22132 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud Lu, Jingjing Pi, Huilong Qin, Yunchuan Tang, Zhuo Li, Ruihui Computer Vision and Pattern Recognition 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. |
| title | Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22132 |