HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916180210483200 |
|---|---|
| author | Xu, Hao Li, Haipeng Wang, Yinqiao Liu, Shuaicheng Fu, Chi-Wing |
| author_facet | Xu, Hao Li, Haipeng Wang, Yinqiao Liu, Shuaicheng Fu, Chi-Wing |
| contents | Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets. While data synthesis helps relieve the issue, the syn-to-real gap still hinders its usage. In this work, we present HandBooster, a new approach to uplift the data diversity and boost the 3D hand-mesh reconstruction performance by training a conditional generative space on hand-object interactions and purposely sampling the space to synthesize effective data samples. First, we construct versatile content-aware conditions to guide a diffusion model to produce realistic images with diverse hand appearances, poses, views, and backgrounds; favorably, accurate 3D annotations are obtained for free. Then, we design a novel condition creator based on our similarity-aware distribution sampling strategies to deliberately find novel and realistic interaction poses that are distinctive from the training set. Equipped with our method, several baselines can be significantly improved beyond the SOTA on the HO3D and DexYCB benchmarks. Our code will be released on https://github.com/hxwork/HandBooster_Pytorch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18575 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions Xu, Hao Li, Haipeng Wang, Yinqiao Liu, Shuaicheng Fu, Chi-Wing Computer Vision and Pattern Recognition Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets. While data synthesis helps relieve the issue, the syn-to-real gap still hinders its usage. In this work, we present HandBooster, a new approach to uplift the data diversity and boost the 3D hand-mesh reconstruction performance by training a conditional generative space on hand-object interactions and purposely sampling the space to synthesize effective data samples. First, we construct versatile content-aware conditions to guide a diffusion model to produce realistic images with diverse hand appearances, poses, views, and backgrounds; favorably, accurate 3D annotations are obtained for free. Then, we design a novel condition creator based on our similarity-aware distribution sampling strategies to deliberately find novel and realistic interaction poses that are distinctive from the training set. Equipped with our method, several baselines can be significantly improved beyond the SOTA on the HO3D and DexYCB benchmarks. Our code will be released on https://github.com/hxwork/HandBooster_Pytorch. |
| title | HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18575 |