Ego-view Accident Video Diffusion
This is our ego-view accident video generation benchmark that can be driven by different text descriptions annotated in MM-AU. The performance is measured by the CLIP Score (CLIPs), Fréchet Video Distance (FVD) and Frames Per Second (FPS). We aim to explore the cause-effect evolution of accident videos conditioned by the descriptions of accident reasons or prevention advice.
Leaderboard
| ID | Method | Year | Code | CLIPs | FVD | FPS | Environment |
|---|---|---|---|---|---|---|---|
| 1 | Tune-A-Video | 2023 | Link | 21.77 | 9545.6 | 1.7 | RTX 3090 |
| 2 | ControlVideo | 2023 | Link | 22.51 | 12275.2 | 0.5 | RTX 3090 |
| 3 | OVAD | 2023 | Link | 27.24 | 5238.1 | 1.2 | RTX 3090 |
| 4 | ModelScope T2V | 2023 | Link | 27.15 | 5088.7 | 1.3 | RTX 3090 |
| 5 | Text2Video-Zero | 2023 | Link | 27.89 | 12547.0 | 1.1 | RTX 3090 |
| 6 | Causal-VidSyn | 2025 | Link | 28.70 | 5352.9 | ... | RTX 3090 |
Submit Your Results
You can submit your metric values via the provided form. Furthermore, we would highly appreciate your contribution with clear links to relevant articles and code for more in-depth analysis.
Click here to submit your results:
Submit