Results for TaoAvatar
Submission info
| Full name | TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting |
|---|---|
| Publication title | TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting |
| Publication authors | Jianchuan Chen, Jingchuan Hu, Gaige Wang, Zhonghua Jiang, Tiansong Zhou, Zhiwen Chen, Chengfei Lv |
| Publication venue | CVPR 2025 |
| Publication url | https://arxiv.org/abs/2503.17032 |
| Project link | |
| Use other data | No |
| Last edited | 21 May, 2025 |
Monocular FLAME Avatar results
Unseen expressions, unseen viewpoints
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Left camera | 17.0838 | 0.7641 | 0.2993 | 4.8090 | 5.4308 | 0.6555 |
| Center camera | 19.1178 | 0.7843 | 0.2584 | 5.3926 | 4.6926 | 0.7229 |
| Right camera | 17.7090 | 0.8142 | 0.2457 | 5.3147 | 6.8537 | 0.6220 |
| Total | 17.9702 | 0.7875 | 0.2678 | 5.1721 | 5.6590 | 0.6668 |
Unseen expressions, train viewpoint
| PSNR | SSIM | LPIPS | JOD | AKD | CSIM | |
|---|---|---|---|---|---|---|
| Train viewpoint | 20.1083 | 0.8053 | 0.2357 | 5.6809 | 3.9480 | 0.7683 |
Generated Images
| Subject ID | Left camera | Center camera | Right camera | Train camera | Ground truth |
|---|---|---|---|---|---|
| 393 |
|
|
|
|
|
| 404 |
|
|
|
|
|
| 461 |
|
|
|
|
|
| 477 |
|
|
|
|
|
| 486 |
|
|
|
|
|