Pose-guided Text-to-3D Human Generation on DeepFashion (test)
21.136FIDCCH
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CCHretrained on face-blurred datasets=true2023.05 | 21.136 | 0.0121 | 88.355 | 25.023 | 72.038 | |
| CLIP-Oretrained on face-blurred datasets=true2023.05 | 25.488 | 0.0133 | 87.892 | 21.887 | 61.964 | |
| TEXTureretrained on face-blurred datasets=true2023.05 | 37.058 | 0.0165 | 86.354 | 23.385 | 67.508 | |
| Latent-NeRFretrained on face-blurred datasets=true2023.05 | 69.654 | 0.0298 | 74.211 | 22.5 | 65.883 |