SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914413892599808 |
|---|---|
| author | Yan, Hongyu Li, Zijun Luo, Kunming Lu, Li Tan, Ping |
| author_facet | Yan, Hongyu Li, Zijun Luo, Kunming Lu, Li Tan, Ping |
| contents | Point cloud completion aims to recover a complete point shape from a partial point cloud. Although existing methods can form satisfactory point clouds in global completeness, they often lose the original geometry details and face the problem of geometric inconsistency between existing point clouds and reconstructed missing parts. To tackle this problem, we introduce SymmCompletion, a highly effective completion method based on symmetry guidance. Our method comprises two primary components: a Local Symmetry Transformation Network (LSTNet) and a Symmetry-Guidance Transformer (SGFormer). First, LSTNet efficiently estimates point-wise local symmetry transformation to transform key geometries of partial inputs into missing regions, thereby generating geometry-align partial-missing pairs and initial point clouds. Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds. As a result, SGFormer can exploit provided priors to form high-fidelity and geometry-consistency final point clouds. Qualitative and quantitative evaluations on several benchmark datasets demonstrate that our method outperforms state-of-the-art completion networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance Yan, Hongyu Li, Zijun Luo, Kunming Lu, Li Tan, Ping Computer Vision and Pattern Recognition Point cloud completion aims to recover a complete point shape from a partial point cloud. Although existing methods can form satisfactory point clouds in global completeness, they often lose the original geometry details and face the problem of geometric inconsistency between existing point clouds and reconstructed missing parts. To tackle this problem, we introduce SymmCompletion, a highly effective completion method based on symmetry guidance. Our method comprises two primary components: a Local Symmetry Transformation Network (LSTNet) and a Symmetry-Guidance Transformer (SGFormer). First, LSTNet efficiently estimates point-wise local symmetry transformation to transform key geometries of partial inputs into missing regions, thereby generating geometry-align partial-missing pairs and initial point clouds. Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds. As a result, SGFormer can exploit provided priors to form high-fidelity and geometry-consistency final point clouds. Qualitative and quantitative evaluations on several benchmark datasets demonstrate that our method outperforms state-of-the-art completion networks. |
| title | SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18007 |