Results for RGBAvatar
Submission info
| Full name | Reduced Gaussian Blendshapes for Online Modeling of Head Avatars |
|---|---|
| Publication title | RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars |
| Publication authors | Linzhou Li, Yumeng Li, Yanlin Weng, Youyi Zheng, Kun Zhou |
| Publication venue | CVPR 2025 |
| Publication url | https://arxiv.org/abs/2503.12886 |
| Project link | http://gapszju.github.io/RGBAvatar |
| Hardware | 3090*1 |
| Use other data | No |
| Last edited | 03 June, 2025 |
Monocular FLAME Avatar results
Unseen expressions, unseen viewpoints
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Left camera | 19.2575 | 0.8053 | 0.2220 | 5.5448 | 3.2024 | 0.8119 |
| Center camera | 22.8360 | 0.8356 | 0.1449 | 6.4784 | 2.4963 | 0.8957 |
| Right camera | 19.8231 | 0.8454 | 0.1769 | 6.0681 | 4.5448 | 0.7640 |
| Total | 20.6388 | 0.8288 | 0.1813 | 6.0305 | 3.4145 | 0.8238 |
Unseen expressions, train viewpoint
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Train viewpoint | 24.3082 | 0.8557 | 0.1226 | 6.8452 | 2.1295 | 0.9120 |
Generated Images
| Subject ID | Left camera | Center camera | Right camera | Train camera | Ground truth |
|---|---|---|---|---|---|
| 393 |
|
|
|
|
|
| 404 |
|
|
|
|
|
| 461 |
|
|
|
|
|
| 477 |
|
|
|
|
|
| 486 |
|
|
|
|
|