Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation

TL;DR

This paper introduces MASC-Pose, a novel framework that adaptively models multi-scale temporal dynamics and uses skeleton-constrained graphs for efficient 3D human pose estimation from videos.

Contribution

It proposes adaptive multi-scale temporal modeling and skeleton-constrained spatial graphs, improving accuracy and efficiency over fixed or dense attention methods.

Findings

Achieves state-of-the-art accuracy on Human3.6M and MPI-INF-3DHP datasets.

Demonstrates high computational efficiency compared to existing methods.

Effectively captures heterogeneous motion dynamics at multiple temporal scales.

Abstract

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.