Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human 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_ | 1866913004975554560 |
|---|---|
| author | Li, Ruochen Chen, Shuang E, Wenke Arvin, Farshad Atapour-Abarghouei, Amir |
| author_facet | Li, Ruochen Chen, Shuang E, Wenke Arvin, Farshad Atapour-Abarghouei, Amir |
| contents | Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges in efficiency and adaptability when modelling spatial and temporal dependencies, particularly under dense attention or fixed modelling schemes. In this work, we propose MASC-Pose, a Motion-Adaptive multi-scale temporal modelling framework with Skeleton-Constrained spatial graphs for efficient 3D human pose estimation. Specifically, it introduces an Adaptive Multi-scale Temporal Modelling (AMTM) module to adaptively capture heterogeneous motion dynamics at different temporal scales, together with a Skeleton-constrained Adaptive GCN (SAGCN) for joint-specific spatial interaction modelling. By jointly enabling adaptive temporal reasoning and efficient spatial aggregation, our method achieves strong accuracy with high computational efficiency. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets demonstrate the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03652 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation Li, Ruochen Chen, Shuang E, Wenke Arvin, Farshad Atapour-Abarghouei, Amir Computer Vision and Pattern Recognition Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges in efficiency and adaptability when modelling spatial and temporal dependencies, particularly under dense attention or fixed modelling schemes. In this work, we propose MASC-Pose, a Motion-Adaptive multi-scale temporal modelling framework with Skeleton-Constrained spatial graphs for efficient 3D human pose estimation. Specifically, it introduces an Adaptive Multi-scale Temporal Modelling (AMTM) module to adaptively capture heterogeneous motion dynamics at different temporal scales, together with a Skeleton-constrained Adaptive GCN (SAGCN) for joint-specific spatial interaction modelling. By jointly enabling adaptive temporal reasoning and efficient spatial aggregation, our method achieves strong accuracy with high computational efficiency. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets demonstrate the effectiveness of our approach. |
| title | Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.03652 |