Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.15648 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913666781151232 |
|---|---|
| author | Knapp, Vaclav Bohacek, Matyas |
| author_facet | Knapp, Vaclav Bohacek, Matyas |
| contents | Recent pose-transfer methods aim to generate temporally consistent and fully controllable videos of human action where the motion from a reference video is reenacted by a new identity. We evaluate three state-of-the-art pose-transfer methods -- AnimateAnyone, MagicAnimate, and ExAvatar -- by generating videos with actions and identities outside the training distribution and conducting a participant study about the quality of these videos. In a controlled environment of 20 distinct human actions, we find that participants, presented with the pose-transferred videos, correctly identify the desired action only 42.92% of the time. Moreover, the participants find the actions in the generated videos consistent with the reference (source) videos only 36.46% of the time. These results vary by method: participants find the splatting-based ExAvatar more consistent and photorealistic than the diffusion-based AnimateAnyone and MagicAnimate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15648 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can Pose Transfer Models Generate Realistic Human Motion? Knapp, Vaclav Bohacek, Matyas Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Recent pose-transfer methods aim to generate temporally consistent and fully controllable videos of human action where the motion from a reference video is reenacted by a new identity. We evaluate three state-of-the-art pose-transfer methods -- AnimateAnyone, MagicAnimate, and ExAvatar -- by generating videos with actions and identities outside the training distribution and conducting a participant study about the quality of these videos. In a controlled environment of 20 distinct human actions, we find that participants, presented with the pose-transferred videos, correctly identify the desired action only 42.92% of the time. Moreover, the participants find the actions in the generated videos consistent with the reference (source) videos only 36.46% of the time. These results vary by method: participants find the splatting-based ExAvatar more consistent and photorealistic than the diffusion-based AnimateAnyone and MagicAnimate. |
| title | Can Pose Transfer Models Generate Realistic Human Motion? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.15648 |