Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914305047265280 |
|---|---|
| author | Cen, Jiaxin Mao, Xudong Yue, Guanghui Zhou, Wei Wang, Ruomei Zhou, Fan Zhao, Baoquan |
| author_facet | Cen, Jiaxin Mao, Xudong Yue, Guanghui Zhou, Wei Wang, Ruomei Zhou, Fan Zhao, Baoquan |
| contents | Monocular video human mesh recovery faces fundamental challenges in maintaining metric consistency and temporal stability due to inherent depth ambiguities and scale uncertainties. While existing methods rely primarily on RGB features and temporal smoothing, they struggle with depth ordering, scale drift, and occlusion-induced instabilities. We propose a comprehensive depth-guided framework that achieves metric-aware temporal consistency through three synergistic components: A Depth-Guided Multi-Scale Fusion module that adaptively integrates geometric priors with RGB features via confidence-aware gating; A Depth-guided Metric-Aware Pose and Shape (D-MAPS) estimator that leverages depth-calibrated bone statistics for scale-consistent initialization; A Motion-Depth Aligned Refinement (MoDAR) module that enforces temporal coherence through cross-modal attention between motion dynamics and geometric cues. Our method achieves superior results on three challenging benchmarks, demonstrating significant improvements in robustness against heavy occlusion and spatial accuracy while maintaining computational efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery Cen, Jiaxin Mao, Xudong Yue, Guanghui Zhou, Wei Wang, Ruomei Zhou, Fan Zhao, Baoquan Computer Vision and Pattern Recognition Monocular video human mesh recovery faces fundamental challenges in maintaining metric consistency and temporal stability due to inherent depth ambiguities and scale uncertainties. While existing methods rely primarily on RGB features and temporal smoothing, they struggle with depth ordering, scale drift, and occlusion-induced instabilities. We propose a comprehensive depth-guided framework that achieves metric-aware temporal consistency through three synergistic components: A Depth-Guided Multi-Scale Fusion module that adaptively integrates geometric priors with RGB features via confidence-aware gating; A Depth-guided Metric-Aware Pose and Shape (D-MAPS) estimator that leverages depth-calibrated bone statistics for scale-consistent initialization; A Motion-Depth Aligned Refinement (MoDAR) module that enforces temporal coherence through cross-modal attention between motion dynamics and geometric cues. Our method achieves superior results on three challenging benchmarks, demonstrating significant improvements in robustness against heavy occlusion and spatial accuracy while maintaining computational efficiency. |
| title | Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.04257 |