Pose-guided Text-to-3D Human Generation on SHHQ (test)
32.858FIDCCH
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CCHretrained on face-blurred datasets=true2023.05 | 32.858 | 0.0165 | 87.624 | 27.855 | 76.194 | |
| CLIP-Oretrained on face-blurred datasets=true2023.05 | 34.212 | 0.0164 | 87.312 | 21.401 | 66.808 | |
| TEXTureretrained on face-blurred datasets=true2023.05 | 48.618 | 0.0216 | 85.502 | 24.456 | 68.233 | |
| Latent-NeRFretrained on face-blurred datasets=true2023.05 | 72.256 | 0.0381 | 73.401 | 22.21 | 67.427 |