Emotional Talking Head Generation on MEAD Cross-ID
45.2Score (Neutral)Wav2Lip-Emo
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Wav2Lip-EmoMetric Group=FAD↓, Backbone=Wav2Lip-Emo2026.04 | 45.2 | — | — | — | 50.15 | 49.8 | 49.3 | 48.95 | 50.5 | 47.83 | 48.819 | |
| ASCCL (Conf.)Metric Group=FAD↓, Backbone=Wav2Lip-Emo2026.04 | 43.5 | — | — | — | 46.8 | 47.1 | 46.5 | 45.9 | 47.2 | 44.8 | 45.971 | |
| Ours_CMMetric Group=FAD↓, Backbone=Wav2Lip-Emo2026.04 | 38.8 | — | — | — | 42.1 | 42.5 | 41.8 | 41.2 | 40.05 | 39.9 | 40.907 | |
| Ours_VDMetric Group=FAD↓, Backbone=Wav2Lip-Emo2026.04 | 36.2 | — | — | — | 39.5 | 39.8 | 38.9 | 38.5 | 40.1 | 37.5 | 38.643 | |
| Wav2Lip-EmoMetric Group=LSE-D↓, Backbone=Wav2Lip-Emo2026.04 | 9.85 | — | — | — | 10.82 | 10.65 | 10.58 | 10.35 | 10.72 | 10.131 | 10.443 | |
| DSMMetric Group=LSE-D↓, Backbone=DSM2026.04 | 9.801 | — | — | — | 9.888 | 10.157 | 9.739 | 9.518 | 9.961 | 10.357 | 9.917 | |
| ASCCL (Conf.)Metric Group=LSE-D↓, Backbone=Wav2Lip-Emo2026.04 | 9.65 | — | — | — | 10.45 | 10.25 | 10.18 | 9.95 | 10.32 | 9.85 | 10.093 | |
| Ours_CMMetric Group=LSE-D↓, Backbone=Wav2Lip-Emo2026.04 | 9.42 | — | — | — | 10.12 | 9.95 | 9.88 | 9.65 | 9.88 | 9.55 | 9.778 | |
| ASCCL (Conf.)Metric Group=LSE-D↓, Backbone=DSM2026.04 | 9.409 | — | — | — | 9.483 | 9.364 | 9.37 | 9.482 | 9.413 | 9.301 | 9.403 | |
| Ours_CMMetric Group=LSE-D↓, Backbone=DSM2026.04 | 9.32 | — | — | — | 9.41 | 9.29 | 9.25 | 9.25 | 9.42 | 9.18 | 9.303 | |
| Ours_VDMetric Group=LSE-D↓, Backbone=DSM2026.04 | 9.25 | — | — | — | 9.3 | 9.22 | 9.18 | 9.15 | 9.35 | 9.12 | 9.224 | |
| Ours_VDMetric Group=LSE-D↓, Backbone=Wav2Lip-Emo2026.04 | 9.25 | — | — | — | 9.85 | 9.72 | 9.68 | 9.45 | 9.95 | 9.32 | 9.593 | |
| ASCCL (Conf.)Metric Group=FAD↓, Backbone=DSM2026.04 | 2.008 | — | — | — | 4.955 | 4.976 | 4.794 | 4.447 | 4.706 | 4.213 | 4.3 | |
| DSMMetric Group=FAD↓, Backbone=DSM2026.04 | 1.916 | — | — | — | 5.071 | 4.991 | 4.686 | 5.274 | 4.943 | 4.338 | 4.46 | |
| Ours_CMMetric Group=FAD↓, Backbone=DSM2026.04 | 1.82 | — | — | — | 4.38 | 4.32 | 4.15 | 4.48 | 4.12 | 3.95 | 3.889 | |
| Ours_VDMetric Group=FAD↓, Backbone=DSM2026.04 | 1.75 | — | — | — | 4.25 | 4.18 | 4.05 | 4.35 | 4.15 | 3.85 | 3.797 | |
| Ours_CMMetric Group=CSIM↑, Backbone=DSM2026.04 | 0.895 | — | — | — | 0.778 | 0.805 | 0.758 | 0.898 | 0.768 | 0.802 | 0.815 | |
| Ours_VDMetric Group=CSIM↑, Backbone=DSM2026.04 | 0.88 | — | — | — | 0.76 | 0.79 | 0.735 | 0.885 | 0.745 | 0.775 | 0.796 | |
| ASCCL (Conf.)Metric Group=CSIM↑, Backbone=DSM2026.04 | 0.877 | — | — | — | 0.755 | 0.785 | 0.726 | 0.88 | 0.737 | 0.769 | 0.79 | |
| DSMMetric Group=CSIM↑, Backbone=DSM2026.04 | 0.866 | — | — | — | 0.753 | 0.784 | 0.737 | 0.777 | 0.744 | 0.787 | 0.778 | |
| Ours_CMMetric Group=CSIM↑, Backbone=Wav2Lip-Emo2026.04 | 0.715 | — | — | — | 0.64 | 0.665 | 0.65 | 0.705 | 0.645 | 0.68 | 0.671 | |
| Ours_VDMetric Group=CSIM↑, Backbone=Wav2Lip-Emo2026.04 | 0.67 | — | — | — | 0.585 | 0.61 | 0.595 | 0.71 | 0.59 | 0.625 | 0.626 | |
| ASCCL (Conf.)Metric Group=CSIM↑, Backbone=Wav2Lip-Emo2026.04 | 0.655 | — | — | — | 0.56 | 0.585 | 0.575 | 0.62 | 0.565 | 0.605 | 0.595 | |
| Wav2Lip-EmoMetric Group=CSIM↑, Backbone=Wav2Lip-Emo2026.04 | 0.62 | — | — | — | 0.51 | 0.535 | 0.52 | 0.58 | 0.515 | 0.556 | 0.548 | |
| ASCCLBackbone=ICface2026.04 | — | 9.48 | 10.375 | 0.726 | — | — | — | — | — | — | — | |
| ASCCLBackbone=NED2026.04 | — | 4.264 | 9.238 | 0.791 | — | — | — | — | — | — | — | |
| ASCCLBackbone=EAT2026.04 | — | 7.35 | 9.75 | 0.718 | — | — | — | — | — | — | — | |
| ASCCLBackbone=DICE-Talk2026.04 | — | 2.59 | 8.98 | 0.785 | — | — | — | — | — | — | — | |
| BaselineBackbone=ICface2026.04 | — | 9.54 | 11.238 | 0.688 | — | — | — | — | — | — | — | |
| BaselineBackbone=NED2026.04 | — | 4.448 | 9.906 | 0.773 | — | — | — | — | — | — | — | |
| BaselineBackbone=EAT2026.04 | — | 7.464 | 10.023 | 0.706 | — | — | — | — | — | — | — | |
| BaselineBackbone=DICE-Talk2026.04 | — | 2.666 | 9.082 | 0.777 | — | — | — | — | — | — | — | |
| Ours_CMBackbone=ICface2026.04 | — | 9.46 | 10.312 | 0.732 | — | — | — | — | — | — | — | |
| Ours_CMBackbone=NED2026.04 | — | 4.253 | 9.225 | 0.799 | — | — | — | — | — | — | — | |
| Ours_CMBackbone=EAT2026.04 | — | 7.256 | 9.389 | 0.74 | — | — | — | — | — | — | — | |
| Ours_CMBackbone=DICE-Talk2026.04 | — | 2.532 | 8.879 | 0.803 | — | — | — | — | — | — | — | |
| Ours_VDBackbone=ICface2026.04 | — | 9.445 | 10.311 | 0.73 | — | — | — | — | — | — | — | |
| Ours_VDBackbone=NED2026.04 | — | 4.169 | 9.216 | 0.795 | — | — | — | — | — | — | — | |
| Ours_VDBackbone=EAT2026.04 | — | 7.198 | 9.381 | 0.733 | — | — | — | — | — | — | — | |
| Ours_VDBackbone=DICE-Talk2026.04 | — | 2.47 | 8.872 | 0.797 | — | — | — | — | — | — | — |