Codesota · Benchmark · KITTI DepthHome/Leaderboards/Vision & Documents/Depth Estimation/KITTI Depth
Unknown

KITTI Depth.

Outdoor depth estimation from autonomous driving LiDAR data

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Absrel

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

Trust tiers for Absrelverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01Marigold
Marigold zero-shot affine-invariant evaluation on KITTI. AbsRel. Table 1 in paper.
verified0.102023Source ↗Looks wrong?
02MiDaS 3.1 (BEiT-512)
MiDaS v3.1 BEiT-512. AbsRel on KITTI Eigen split. Reported in Depth Anything Table 1.
verified0.062024Source ↗Looks wrong?
03ZoeDepth-K
ZoeDepth-K fine-tuned on KITTI. AbsRel on Eigen test split. Table 2 in paper.
verified0.052023Source ↗Looks wrong?
04Depth Anything V1 (ViT-L)
Depth Anything V1 ViT-L fine-tuned on KITTI. AbsRel on Eigen split. Table 1.
verified0.052024Source ↗Looks wrong?
05Depth Anything V2 (ViT-L)
Depth Anything V2 ViT-L, fine-tuned metric model. AbsRel on KITTI Eigen split. Table 2.
verified0.042024Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Depth Estimation