SyncAI.news, a Varaisys broadcasting
Structure-Guided Multi-Granularity Spatiotemporal Transformer for Efficient Monocular 3D Human Pose Estimation
SX

Sheng Xu, Aoduo Li, Rongli He

· 1 min read

ResearcharXiv cs.AI

Structure-Guided Multi-Granularity Spatiotemporal Transformer for Efficient Monocular 3D Human Pose Estimation

arXiv:2611.20361v1 Announce Type: cross Abstract: Existing multi-granularity methods for monocular 3D human pose estimation emphasize spatial joint features while underusing skeletal structure, including global connectivity and temporal continuity. Moreover, modeling entire frame sequences incurs high computational costs. We propose a Structure-Aware Multi-Granularity Spatiotemporal Transformer that integrates structural priors across spatial and temporal representations for accurate and efficient pose estimation. A three-level feature extractor captures human topology at the joint, bone, and limb levels. Gated Adaptive Spatial Attention (GASA) embeds structural constraints into spatial attention, while Multi-Granularity Feature Enhancement (MGFE) uses hierarchical pooling and fusion to strengthen local details and global semantics. Temporal Segment Fusion (TSF) aligns temporal contexts across granularities to capture both short- and long-range motion patterns. Hierarchical Cross-Attention (HCA) promotes spatiotemporal interaction between granularities, and Keyframe Attention (KFA) selects informative motion segments to reduce redundancy and computational cost. Experiments demonstrate improved accuracy and efficiency over conventional Transformer-based approaches, highlighting the effectiveness of structure-aware multi-granularity modeling for monocular 3D human pose estimation.

Original source

This story was published by arXiv cs.AI and written by Sheng Xu, Aoduo Li, Rongli He. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News