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/abs/2412.12093 |
| Project link | https://felixtaubner.github.io/cap4d/ |
| Hardware | RTX6000 x 4 |
| Use other data | No |
| Last edited | 28 May, 2025 |
Monocular FLAME Avatar results
Unseen expressions, unseen viewpoints
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Left camera | 18.8634 | 0.8008 | 0.2155 | 5.4092 | 4.2671 | 0.7757 |
| Center camera | 20.1786 | 0.8154 | 0.1680 | 5.8902 | 3.8719 | 0.8476 |
| Right camera | 20.2594 | 0.8481 | 0.1702 | 6.0629 | 4.4375 | 0.7559 |
| Total | 19.7671 | 0.8214 | 0.1846 | 5.7874 | 4.1922 | 0.7930 |
Unseen expressions, train viewpoint
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Train viewpoint | 21.1153 | 0.8260 | 0.1445 | 6.1252 | 3.6067 | 0.8606 |
Generated Images
| Subject ID | Left camera | Center camera | Right camera | Train camera | Ground truth |
|---|---|---|---|---|---|
| 393 |
|
|
|
|
|
| 404 |
|
|
|
|
|
| 461 |
|
|
|
|
|
| 477 |
|
|
|
|
|
| 486 |
|
|
|
|
|