AI Paper Atlas

Research map / 3D vision / Depth and stereo

MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources

Jiahui Yang, Donglin Di, Xuancheng Zhang, Lei Fan, Jianxun Cui, Hao Li, Baorui Ma

ECCV 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale pretraining data from 5% to 100% (ablation)MetricAnything-Pretrain · KITTI 8x depth super-resolutionAbsRel: 5.22 -> 2.34Improved
replace U-Net skip with inverse skip, pseudo labels (ablation)Student model · NuScenesAbs: 0.187 -> 0.125Improved
replace U-Net skip with inverse skip, pseudo labels (ablation)Student model · ETH3DAbs: 0.269 -> 0.182Improved
replace U-Net skip with inverse skip, real-world labels (ablation)Student model · NuScenesAbs: 0.213 -> 0.235Hurt
train with pseudo labels instead of real-world labels (ablation)Student model · NuScenesAbs: 0.235 -> 0.125Improved
use distance-balanced inverse-depth loss instead of inverse-depth (ablation)MetricAnything · DIODE >50mAbsRel: 0.632 -> 0.589Improved
use distance-balanced loss instead of inverse-depth at close range (ablation)MetricAnything · DIODE 0-10mAbsRel: 0.467 -> 0.465No clear effect
increase sparse prompt points from 500 to 64000 (ablation)MetricAnything · HypersimAbsRel: 0.043 -> 0.031Improved
increase prompt points from 500 to 64000 (ablation)MetricAnything · Hypersimtime (ms): 224 -> 308Hurt
increase balance coefficient C from 50 to 600 (ablation)distance-balanced loss · DIODE 0-40mAbsRel: 0.441 -> 0.465Hurt
increase balance coefficient C from 50 to 600 (ablation)distance-balanced loss · DIODE >40mAbsRel: 0.635 -> 0.559Improved
finetune pretrained model instead of training from scratch (ablation)MetricAnything · nuScenes radar 0-50mMAE (mm): 1335.4 -> 651.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy