DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911510882680832 |
|---|---|
| author | Wang, Renke Zhang, Zhenyu Tai, Ying Li, Jun Yang, Jian |
| author_facet | Wang, Renke Zhang, Zhenyu Tai, Ying Li, Jun Yang, Jian |
| contents | Precise human mesh recovery (HMR) from multi-view images remains challenging: end-to-end methods produce entangled errors hard to localize, while fitting-based methods rely on sparse keypoints that provide limited surface constraints. We observe that the true bottleneck lies in the quality of intermediate representations, and that dense pixel-to-surface correspondences can be effectively generated by repurposing pre-trained diffusion models with rich visual priors. We propose DiffProxy, a Stable-Diffusion-based framework trained on large-scale synthetic data with pixel-perfect annotations. A multi-conditional proxy generator predicts dense correspondences from multi-view images, providing uniform surface constraints that enable precise fitting. Hand refinement feeds enlarged hand crops alongside full-body images for fine-grained detail, while test-time scaling exploits diffusion stochasticity to estimate per-pixel uncertainty. Trained only on synthetic data, DiffProxy achieves state-of-the-art results on five diverse real-world benchmarks. Project page: https://wrk226.github.io/DiffProxy.html |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02267 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies Wang, Renke Zhang, Zhenyu Tai, Ying Li, Jun Yang, Jian Computer Vision and Pattern Recognition Precise human mesh recovery (HMR) from multi-view images remains challenging: end-to-end methods produce entangled errors hard to localize, while fitting-based methods rely on sparse keypoints that provide limited surface constraints. We observe that the true bottleneck lies in the quality of intermediate representations, and that dense pixel-to-surface correspondences can be effectively generated by repurposing pre-trained diffusion models with rich visual priors. We propose DiffProxy, a Stable-Diffusion-based framework trained on large-scale synthetic data with pixel-perfect annotations. A multi-conditional proxy generator predicts dense correspondences from multi-view images, providing uniform surface constraints that enable precise fitting. Hand refinement feeds enlarged hand crops alongside full-body images for fine-grained detail, while test-time scaling exploits diffusion stochasticity to estimate per-pixel uncertainty. Trained only on synthetic data, DiffProxy achieves state-of-the-art results on five diverse real-world benchmarks. Project page: https://wrk226.github.io/DiffProxy.html |
| title | DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.02267 |