NeRSemble
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Novel Expression Synthesis | NeRSemble | PSNR36.56 | 30 | |
| 3D Face Reconstruction | NeRSemble-SVFR (Posed) | L1 Error1.37 | 10 | |
| Monocular 3D Head Avatar Creation | NeRSemble | PSNR20.9 | 8 | |
| Video-driven Talking Head Generation (Cross-Reenactment) | NeRSemble Mono | FID57.82 | 7 | |
| Video-driven Talking Head Generation (Self-Reenactment) | NeRSemble Mono | PSNR31.98 | 7 | |
| Cross Reenactment | NeRSemble | AED0.1709 | 6 | |
| Cross Reenactment | Nersemble (test) | CSIM85.49 | 6 | |
| Self Reenactment | Nersemble (test) | PSNR22.6313 | 6 | |
| Novel View Synthesis | NeRSemble (test) | PSNR27.54 | 6 | |
| Motion-conditioned Image-to-Video Animation | NeRSemble (test) | Hair SSIM0.967 | 6 | |
| Novel View Synthesis | NeRSemble (val) | PSNR22.76 | 5 | |
| Self-Reenactment | NeRSemble (val) | PSNR22.21 | 5 | |
| Novel View Synthesis | NeRSemble (novel-view split) | PSNR33.5528 | 5 | |
| Novel expression and view synthesis | NeRSemble (novel expressions and views) | PSNR32.6781 | 5 | |
| Avatar Synthesis | NeRSemble Single Image (test) | PSNR20.73 | 5 | |
| 3D Portrait Reconstruction | NeRSemble (test) | Expr Score0.158 | 5 | |
| 3D-aware talking portrait generation | NeRSemble (novel views) | FID29.52 | 4 | |
| Cross Reenactment | NeRSemble multi-view v2 (test) | CSIM0.666 | 4 | |
| Self Reenactment | NeRSemble multi-view v2 (test) | PSNR22.5 | 4 | |
| Head Avatar Generation | Nersemble (test) | PSNR23.002 | 4 | |
| 3D head avatar reconstruction | NeRSemble | PSNR24 | 4 | |
| Avatar Synthesis | NeRSemble Monocular Video (test) | PSNR21.34 | 4 | |
| Avatar Reconstruction | NeRSemble (unseen freeform sequence) | PSNR24.73 | 4 |
Showing 23 of 23 rows