SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation
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_ | 1866914152918810624 |
|---|---|
| author | Cui, Hu Hua, Wenqiang Huang, Renjing Jia, Shurui Hayama, Tessai |
| author_facet | Cui, Hu Hua, Wenqiang Huang, Renjing Jia, Shurui Hayama, Tessai |
| contents | Recently, the Mamba architecture based on State Space Models (SSMs) has gained attention in 3D human pose estimation due to its linear complexity and strong global modeling capability. However, existing SSM-based methods typically apply manually designed scan operations to flatten detected 2D pose sequences into purely temporal sequences, either locally or globally. This approach disrupts the inherent spatial structure of human poses and entangles spatial and temporal features, making it difficult to capture complex pose dependencies. To address these limitations, we propose the Skeleton Structure-Aware Stride SSM (SAS-SSM), which first employs a structure-aware spatiotemporal convolution to dynamically capture essential local interactions between joints, and then applies a stride-based scan strategy to construct multi-scale global structural representations. This enables flexible modeling of both local and global pose information while maintaining linear computational complexity. Built upon SAS-SSM, our model SasMamba achieves competitive 3D pose estimation performance with significantly fewer parameters compared to existing hybrid models. The source code is available at https://hucui2022.github.io/sasmamba_proj/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08872 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation Cui, Hu Hua, Wenqiang Huang, Renjing Jia, Shurui Hayama, Tessai Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Recently, the Mamba architecture based on State Space Models (SSMs) has gained attention in 3D human pose estimation due to its linear complexity and strong global modeling capability. However, existing SSM-based methods typically apply manually designed scan operations to flatten detected 2D pose sequences into purely temporal sequences, either locally or globally. This approach disrupts the inherent spatial structure of human poses and entangles spatial and temporal features, making it difficult to capture complex pose dependencies. To address these limitations, we propose the Skeleton Structure-Aware Stride SSM (SAS-SSM), which first employs a structure-aware spatiotemporal convolution to dynamically capture essential local interactions between joints, and then applies a stride-based scan strategy to construct multi-scale global structural representations. This enables flexible modeling of both local and global pose information while maintaining linear computational complexity. Built upon SAS-SSM, our model SasMamba achieves competitive 3D pose estimation performance with significantly fewer parameters compared to existing hybrid models. The source code is available at https://hucui2022.github.io/sasmamba_proj/. |
| title | SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.08872 |