Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.04399 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910687239864320 |
|---|---|
| author | Wang, Hongsheng Feng, Zehui Xiao, Tong Yang, Genfan Zhang, Shengyu Wu, Fei Lin, Feng |
| author_facet | Wang, Hongsheng Feng, Zehui Xiao, Tong Yang, Genfan Zhang, Shengyu Wu, Fei Lin, Feng |
| contents | Current 3D human motion reconstruction methods from monocular videos rely on features within the current reconstruction window, leading to distortion and deformations in the human structure under local occlusions or blurriness in video frames. To estimate realistic 3D human mesh sequences based on incomplete features, we propose Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction (ProGraph). For missing parts recovery, we exploit the explicit topological-aware probability distribution across the entire motion sequence. To restore the complete human, Graph Topological Modeling (GTM) learns the underlying topological structure, focusing on the relationships inherent in the individual parts. Next, to generate blurred motion parts, Temporal-alignable Probability Distribution (TPDist) utilizes the GTM to predict features based on distribution. This interactive mechanism facilitates motion consistency, allowing the restoration of human parts. Furthermore, Hierarchical Human Loss (HHLoss) constrains the probability distribution errors of inter-frame features during topological structure variation. Our Method achieves superior results than other SOTA methods in addressing occlusions and blurriness on 3DPW. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04399 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ProGraph: Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction Wang, Hongsheng Feng, Zehui Xiao, Tong Yang, Genfan Zhang, Shengyu Wu, Fei Lin, Feng Computer Vision and Pattern Recognition Current 3D human motion reconstruction methods from monocular videos rely on features within the current reconstruction window, leading to distortion and deformations in the human structure under local occlusions or blurriness in video frames. To estimate realistic 3D human mesh sequences based on incomplete features, we propose Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction (ProGraph). For missing parts recovery, we exploit the explicit topological-aware probability distribution across the entire motion sequence. To restore the complete human, Graph Topological Modeling (GTM) learns the underlying topological structure, focusing on the relationships inherent in the individual parts. Next, to generate blurred motion parts, Temporal-alignable Probability Distribution (TPDist) utilizes the GTM to predict features based on distribution. This interactive mechanism facilitates motion consistency, allowing the restoration of human parts. Furthermore, Hierarchical Human Loss (HHLoss) constrains the probability distribution errors of inter-frame features during topological structure variation. Our Method achieves superior results than other SOTA methods in addressing occlusions and blurriness on 3DPW. |
| title | ProGraph: Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.04399 |