Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.08981 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918090206347264 |
|---|---|
| author | Cho, Hanbyel Ahn, Jaesung Cho, Yooshin Kim, Junmo |
| author_facet | Cho, Hanbyel Ahn, Jaesung Cho, Yooshin Kim, Junmo |
| contents | Human Mesh Recovery (HMR) from an image is a challenging problem because of the inherent ambiguity of the task. Existing HMR methods utilized either temporal information or kinematic relationships to achieve higher accuracy, but there is no method using both. Hence, we propose "Video Inference for Human Mesh Recovery with Vision Transformer (HMR-ViT)" that can take into account both temporal and kinematic information. In HMR-ViT, a Temporal-kinematic Feature Image is constructed using feature vectors obtained from video frames by an image encoder. When generating the feature image, we use a Channel Rearranging Matrix (CRM) so that similar kinematic features could be located spatially close together. The feature image is then further encoded using Vision Transformer, and the SMPL pose and shape parameters are finally inferred using a regression network. Extensive evaluation on the 3DPW and Human3.6M datasets indicates that our method achieves a competitive performance in HMR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08981 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Video Inference for Human Mesh Recovery with Vision Transformer Cho, Hanbyel Ahn, Jaesung Cho, Yooshin Kim, Junmo Computer Vision and Pattern Recognition Human Mesh Recovery (HMR) from an image is a challenging problem because of the inherent ambiguity of the task. Existing HMR methods utilized either temporal information or kinematic relationships to achieve higher accuracy, but there is no method using both. Hence, we propose "Video Inference for Human Mesh Recovery with Vision Transformer (HMR-ViT)" that can take into account both temporal and kinematic information. In HMR-ViT, a Temporal-kinematic Feature Image is constructed using feature vectors obtained from video frames by an image encoder. When generating the feature image, we use a Channel Rearranging Matrix (CRM) so that similar kinematic features could be located spatially close together. The feature image is then further encoded using Vision Transformer, and the SMPL pose and shape parameters are finally inferred using a regression network. Extensive evaluation on the 3DPW and Human3.6M datasets indicates that our method achieves a competitive performance in HMR. |
| title | Video Inference for Human Mesh Recovery with Vision Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.08981 |