kitti-depth is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for kitti-depth.
Absrel is the reported evaluation metric for kitti-depth. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | Marigold | verified | 0.10 | 2026 | Source ↗ | Looks wrong? |
| 02 | MiDaS 3.1 (BEiT-512) | verified | 0.06 | 2026 | Source ↗ | Looks wrong? |
| 03 | ZoeDepth-K | verified | 0.05 | 2026 | Source ↗ | Looks wrong? |
| 04 | Depth Anything V1 (ViT-L) | verified | 0.05 | 2026 | Source ↗ | Looks wrong? |
| 05 | Depth Anything V2 (ViT-L) | verified | 0.04 | 2026 | Source ↗ | Looks wrong? |