in the wild
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio Deepfake Detection | In-the-wild | EER0.8 | 58 | |
| Pixel-level Forgery Localization | In-the-wild | F1 Score69.18 | 11 | |
| Image-level forgery detection | In-the-wild | F1 Score100 | 11 | |
| Bounding Box Localization | In-the-wild | BBox IoU63.54 | 10 | |
| Ordinal consistency | In-the-wild 100 steps horizon v1 (test) | Kendall's Tau0.61 | 8 | |
| Ordinal consistency | In-the-wild 50 steps horizon v1 (test) | Kendall's Tau0.69 | 8 | |
| Voice Anti-spoofing | In-the-Wild (test) | EER6.71 | 7 | |
| Face Reenactment | in the wild | AU %82.3 | 7 | |
| Novel View Synthesis | In-the-Wild Composite | PSNR26.94 | 6 | |
| Novel View Synthesis | In-the-wild data | PSNR29.26 | 6 | |
| Music-driven 2D dance generation | In-the-Wild leakage-free (test) | FID45.2 | 5 | |
| 6D Object Tracking | In the wild instructional and egocentric videos | Relative Depth0.08 | 5 | |
| Face Tracking and Reconstruction | in-the-wild (test) | L2 Distance12.59 | 5 | |
| HOI Video Generation | in-the-wild dataset (test) | Fréchet Video Distance (FVD)484 | 4 | |
| Image-to-image relighting | In-the-wild Stage-wise Study | Lighting Alignment75 | 4 | |
| Image-to-image relighting | In-the-wild Comparison Study | Lighting Alignment0.931 | 3 | |
| 3D Human Reconstruction | In-the-wild Fashion images | Preference Rate (vs ECON)0.551 | 3 | |
| 3D Human Reconstruction | In-the-wild Loose clothing | Preference Rate (vs ECON)36.2 | 3 | |
| 3D Human Reconstruction | In-the-wild Challenging poses | Preference Rate (vs ECON)28.3 | 3 | |
| Talking Face Generation | In-the-wild | Metric- | 0 |
Showing 20 of 20 rows