Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.13479 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912985892519936 |
|---|---|
| author | Wang, Linhao Zhang, Qichang Yang, Yifan Su, Ye Wang, Hao |
| author_facet | Wang, Linhao Zhang, Qichang Yang, Yifan Su, Ye Wang, Hao |
| contents | As 3D point clouds become the prevailing shape representation in computer vision, generating high-quality point clouds remains a challenging problem. Flow-based models have shown strong potential due to exact likelihood estimation and invertible mappings. However, existing flow-based methods for point clouds typically rely on point-wise feature extractors, which limits their ability to model long-range dependencies and global structural relationships among points. Inspired by the wide adoption of Transformers, we explored the complementary roles of self-attention mechanisms, CNN, and flow-based model. To this end, we propose EAGLE, a probabilistic generative model that integrates self-attention mechanisms with adaptive continuous normalizing flows. The self-attention module explicitly models pairwise dependencies among points, enabling effective capture of global contextual information. In addition, we introduce an adaptive bias correction mechanism within flow-based models, which dynamically adjusts to different input contexts and alleviates bias-drift issues. Extensive experiments on ShapeNet and ModelNet datasets demonstrate the effectiveness of our proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention Wang, Linhao Zhang, Qichang Yang, Yifan Su, Ye Wang, Hao Signal Processing As 3D point clouds become the prevailing shape representation in computer vision, generating high-quality point clouds remains a challenging problem. Flow-based models have shown strong potential due to exact likelihood estimation and invertible mappings. However, existing flow-based methods for point clouds typically rely on point-wise feature extractors, which limits their ability to model long-range dependencies and global structural relationships among points. Inspired by the wide adoption of Transformers, we explored the complementary roles of self-attention mechanisms, CNN, and flow-based model. To this end, we propose EAGLE, a probabilistic generative model that integrates self-attention mechanisms with adaptive continuous normalizing flows. The self-attention module explicitly models pairwise dependencies among points, enabling effective capture of global contextual information. In addition, we introduce an adaptive bias correction mechanism within flow-based models, which dynamically adjusts to different input contexts and alleviates bias-drift issues. Extensive experiments on ShapeNet and ModelNet datasets demonstrate the effectiveness of our proposed method. |
| title | EAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2503.13479 |