TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911604124155904 |
|---|---|
| author | Liu, Jinshuo Ma, Bingtao Su, Junlin Pan, Guanyuan Wu, Beining Yang, Cheng Lu, Jiaxuan Yan, Chenggang Wang, Shuai |
| author_facet | Liu, Jinshuo Ma, Bingtao Su, Junlin Pan, Guanyuan Wu, Beining Yang, Cheng Lu, Jiaxuan Yan, Chenggang Wang, Shuai |
| contents | Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a \textbf{T}opology-Aware Learning with \textbf{S}emantic \textbf{M}amba for Category-Level \textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation of the point cloud, which is integrated into local geometry features and enables robust category-level structural representation. Simultaneously, we propose a Mamba-based Global Semantic Aggregator that injects semantics priors into keypoints to enhance their expressiveness and leverages multiple TwinMamba blocks to model long-range dependencies for more effective global feature aggregation. Extensive experiments on three benchmark datasets (REAL275, CAMERA25, and HouseCat6D) demonstrate that TSM-Pose outperforms existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16954 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation Liu, Jinshuo Ma, Bingtao Su, Junlin Pan, Guanyuan Wu, Beining Yang, Cheng Lu, Jiaxuan Yan, Chenggang Wang, Shuai Computer Vision and Pattern Recognition Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a \textbf{T}opology-Aware Learning with \textbf{S}emantic \textbf{M}amba for Category-Level \textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation of the point cloud, which is integrated into local geometry features and enables robust category-level structural representation. Simultaneously, we propose a Mamba-based Global Semantic Aggregator that injects semantics priors into keypoints to enhance their expressiveness and leverages multiple TwinMamba blocks to model long-range dependencies for more effective global feature aggregation. Extensive experiments on three benchmark datasets (REAL275, CAMERA25, and HouseCat6D) demonstrate that TSM-Pose outperforms existing state-of-the-art methods. |
| title | TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.16954 |