Spectral Informed Mamba for Robust Point Cloud Processing
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_ | 1866913756292841472 |
|---|---|
| author | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiechi, David Hakim, Gustavo Adolfo Vargas Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian |
| author_facet | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiechi, David Hakim, Gustavo Adolfo Vargas Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian |
| contents | State space models have shown significant promise in Natural Language Processing (NLP) and, more recently, computer vision. This paper introduces a new methodology leveraging Mamba and Masked Autoencoder networks for point cloud data in both supervised and self-supervised learning. We propose three key contributions to enhance Mamba's capability in processing complex point cloud structures. First, we exploit the spectrum of a graph Laplacian to capture patch connectivity, defining an isometry-invariant traversal order that is robust to viewpoints and better captures shape manifolds than traditional 3D grid-based traversals. Second, we adapt segmentation via a recursive patch partitioning strategy informed by Laplacian spectral components, allowing finer integration and segment analysis. Third, we address token placement in Masked Autoencoder for Mamba by restoring tokens to their original positions, which preserves essential order and improves learning. Extensive experiments demonstrate the improvements of our approach in classification, segmentation, and few-shot tasks over state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spectral Informed Mamba for Robust Point Cloud Processing Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiechi, David Hakim, Gustavo Adolfo Vargas Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian Computer Vision and Pattern Recognition State space models have shown significant promise in Natural Language Processing (NLP) and, more recently, computer vision. This paper introduces a new methodology leveraging Mamba and Masked Autoencoder networks for point cloud data in both supervised and self-supervised learning. We propose three key contributions to enhance Mamba's capability in processing complex point cloud structures. First, we exploit the spectrum of a graph Laplacian to capture patch connectivity, defining an isometry-invariant traversal order that is robust to viewpoints and better captures shape manifolds than traditional 3D grid-based traversals. Second, we adapt segmentation via a recursive patch partitioning strategy informed by Laplacian spectral components, allowing finer integration and segment analysis. Third, we address token placement in Masked Autoencoder for Mamba by restoring tokens to their original positions, which preserves essential order and improves learning. Extensive experiments demonstrate the improvements of our approach in classification, segmentation, and few-shot tasks over state-of-the-art baselines. |
| title | Spectral Informed Mamba for Robust Point Cloud Processing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04953 |