You are currently on the new version of our website. Access the old version .
MathematicsMathematics
  • This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
  • Article
  • Open Access

21 January 2026

Temporal Probability-Guided Graph Topology Learning for Robust 3D Human Mesh Reconstruction

,
,
and
1
School of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
2
School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China
3
School of Vehicles and Intelligent Transportation, Fuyao University of Science and Technology, Fuzhou 350109, China
*
Author to whom correspondence should be addressed.
Mathematics2026, 14(2), 367;https://doi.org/10.3390/math14020367 
(registering DOI)
This article belongs to the Special Issue Advanced Control of Complex Dynamical Systems and Robotics with Applications, 2nd Edition

Abstract

Reconstructing 3D human motion from monocular video presents challenges when frames contain occlusions or blur, as conventional approaches depend on features extracted within limited temporal windows, resulting in structural distortions. In this paper, we introduce a novel framework that combines temporal probability guidance with graph topology learning to achieve robust 3D human mesh reconstruction from incomplete observations. Our method leverages topology-aware probability distributions spanning entire motion sequences to recover missing anatomical regions. The Graph Topological Modeling (GTM) component captures structural relationships among body parts by learning the inherent connectivity patterns in human anatomy. Building upon GTM, our Temporal-alignable Probability Distribution (TPDist) mechanism predicts missing features through probabilistic inference, establishing temporal coherence across frames. Additionally, we propose a Hierarchical Human Loss (HHLoss) that hierarchically regularizes probability distribution errors for inter-frame features while accounting for topological variations. Experimental validation demonstrates that our approach outperforms state-of-the-art methods on the 3DPW benchmark, particularly excelling in scenarios involving occlusions and motion blur.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.