Video Semantic Segmentation on 1024x512 resolution (video)
18.15Speed (FPS)Time2General
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Time2GeneralBackbone=DINOv2-L2026.02 | 18.15 | 24.46 | |
| SSPBackbone=SAM-S2026.02 | 10.99 | 61.62 | |
| REINBackbone=DINOv2-L2026.02 | 6.25 | 23.56 | |
| TV3SBackbone=MiT-B52026.02 | 6.15 | 85.48 | |
| FADABackbone=DINOv2-L2026.02 | 3.93 | 22.64 | |
| DepthForgeBackbone=DINOv2-L2026.02 | 3.85 | 27.9 |