Results for CAP4D
Submission info
| Full name | CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models |
|---|---|
| Publication title | CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models |
| Publication authors | Felix Taubner, Ruihang Zhang, Mathieu Tuli, David B. Lindell |
| Publication venue | CVPR 2025 |
| Publication url | https://arxiv.org/pdf/2412.12093 |
| Project link | https://felixtaubner.github.io/cap4d/ |
| Use other data | No |
| Last edited | 10 May, 2025 |
Monocular FLAME Avatar results
Unseen expressions, unseen viewpoints
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Left camera | 17.5383 | 0.7985 | 0.2405 | 5.2281 | 4.1604 | 0.7646 |
| Center camera | 18.7936 | 0.8117 | 0.2063 | 5.6631 | 3.6825 | 0.8384 |
| Right camera | 20.9057 | 0.8532 | 0.1795 | 6.1409 | 4.2146 | 0.7379 |
| Total | 19.0792 | 0.8211 | 0.2088 | 5.6773 | 4.0192 | 0.7803 |
Unseen expressions, train viewpoint
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Train viewpoint | 19.2213 | 0.8200 | 0.1928 | 5.7523 | 3.4811 | 0.8488 |
Generated Images
| Subject ID | Left camera | Center camera | Right camera | Train camera | Ground truth |
|---|---|---|---|---|---|
| 393 |
|
|
|
|
|
| 404 |
|
|
|
|
|
| 461 |
|
|
|
|
|
| 477 |
|
|
|
|
|
| 486 |
|
|
|
|
|