ViViD
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Monocular Visual Odometry | VIVID Mean over sequences | ATE RMSE0.23 | 20 | |
| Monocular Visual Odometry | VIVID in_rob_local | ATE RMSE0.05 | 18 | |
| Monocular Visual Odometry | VIVID in_unst_local | ATE RMSE0.04 | 17 | |
| Monocular Visual Odometry | VIVID in_rob_global | ATE RMSE0.07 | 17 | |
| Monocular Visual Odometry | VIVID in_rob_dark | ATE RMSE0.04 | 16 | |
| Monocular Visual Odometry | VIVID in_unst_global | ATE RMSE0.04 | 15 | |
| Monocular Visual Odometry | VIVID in_agg_global | ATE RMSE0.08 | 14 | |
| Monocular Visual Odometry | VIVID in_unst_dark | ATE RMSE0.06 | 13 | |
| Video Virtual Try-On | ViViD (test) | SSIM0.9023 | 13 | |
| Monocular Visual Odometry | VIVID in_agg_dark | ATE RMSE0.09 | 12 | |
| Novel View Synthesis | VIVID Thermal Sequences | PSNR (IRD)28.73 | 5 | |
| Novel View Synthesis | VIVID RGB Sequences | PSNR (IRG)28.03 | 5 | |
| Monocular SLAM | ViViD++ global robust sequence | Tracking Percentage100 | 4 | |
| Scene-aware visually driven speech synthesis | Vivid-210K (test) | WER7.15 | 3 |
Showing 14 of 14 rows