Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning
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_ | 1866913929431613440 |
|---|---|
| author | Cao, Xin Wang, Haoyu Mao, Yuzhu Liu, Xinda Su, Linzhi Li, Kang |
| author_facet | Cao, Xin Wang, Haoyu Mao, Yuzhu Liu, Xinda Su, Linzhi Li, Kang |
| contents | Self-supervised learning has emerged as a prominent research direction in point cloud processing. While existing models predominantly concentrate on reconstruction tasks at higher encoder layers, they often neglect the effective utilization of low-level local features, which are typically employed solely for activation computations rather than directly contributing to reconstruction tasks. To overcome this limitation, we introduce PointAMaLR, a novel self-supervised learning framework that enhances feature representation and processing accuracy through attention-guided multi-scale local reconstruction. PointAMaLR implements hierarchical reconstruction across multiple local regions, with lower layers focusing on fine-scale feature restoration while upper layers address coarse-scale feature reconstruction, thereby enabling complex inter-patch interactions. Furthermore, to augment feature representation capabilities, we incorporate a Local Attention (LA) module in the embedding layer to enhance semantic feature understanding. Comprehensive experiments on benchmark datasets ModelNet and ShapeNet demonstrate PointAMaLR's superior accuracy and quality in both classification and reconstruction tasks. Moreover, when evaluated on the real-world dataset ScanObjectNN and the 3D large scene segmentation dataset S3DIS, our model achieves highly competitive performance metrics. These results not only validate PointAMaLR's effectiveness in multi-scale semantic understanding but also underscore its practical applicability in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04084 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning Cao, Xin Wang, Haoyu Mao, Yuzhu Liu, Xinda Su, Linzhi Li, Kang Graphics Computer Vision and Pattern Recognition Self-supervised learning has emerged as a prominent research direction in point cloud processing. While existing models predominantly concentrate on reconstruction tasks at higher encoder layers, they often neglect the effective utilization of low-level local features, which are typically employed solely for activation computations rather than directly contributing to reconstruction tasks. To overcome this limitation, we introduce PointAMaLR, a novel self-supervised learning framework that enhances feature representation and processing accuracy through attention-guided multi-scale local reconstruction. PointAMaLR implements hierarchical reconstruction across multiple local regions, with lower layers focusing on fine-scale feature restoration while upper layers address coarse-scale feature reconstruction, thereby enabling complex inter-patch interactions. Furthermore, to augment feature representation capabilities, we incorporate a Local Attention (LA) module in the embedding layer to enhance semantic feature understanding. Comprehensive experiments on benchmark datasets ModelNet and ShapeNet demonstrate PointAMaLR's superior accuracy and quality in both classification and reconstruction tasks. Moreover, when evaluated on the real-world dataset ScanObjectNN and the 3D large scene segmentation dataset S3DIS, our model achieves highly competitive performance metrics. These results not only validate PointAMaLR's effectiveness in multi-scale semantic understanding but also underscore its practical applicability in real-world scenarios. |
| title | Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04084 |