AI Paper Atlas

Research map / 3D vision / Depth and stereo

Honey, I Shrunk the Arc de Triomphe!

Yuanbo Xiangli, Hanyu Chen, Xueqing Tsang, Noah Snavely

ECCV 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 0 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
fine-tune MoGe-2 on MetricScenesMoGe-2 · MetricScenes test setmetric depth Rel^d (w/o GT cam): 37.2 -> 26.5Improved
fine-tune MoGe-2 on MetricScenesMoGe-2 · MetricScenes test setmetric depth delta1 (w/o GT cam): 37.7 -> 73.8Improved
fine-tune MoGe-2 on MetricScenesMoGe-2 · MetricScenes test setmetric point Rel^p: 11.7 -> 7.59Improved
fine-tune MoGe-2 on MetricScenesMoGe-2 · 10 standard benchmarksmetric depth Rel^d (w/o GT cam): 15.7 -> 15.6No clear effect
fine-tune MoGe-2 on MetricScenesMoGe-2 · 10 standard benchmarksmetric point Rel^p: 8.19 -> 8.39Hurt
fine-tune MoGe-2 on MetricScenesMoGe-2 · 10 standard benchmarksscale-invariant point Rel^p: 10.8 -> 10.1Improved
add AerialMegaDepth and MegaScenes to Stereo4D training (ablation)WildMoGe · MetricScenes test setmetric depth Rel^d (w/o GT cam): 34.0 -> 26.5Improved
add Stereo4D to AerialMegaDepth + MegaScenes training (ablation)WildMoGe · MetricScenes test setmetric depth Rel^d (w/o GT cam): 32.7 -> 26.5Improved
add MegaScenes to AerialMegaDepth training (ablation)WildMoGe · MetricScenes test setmetric depth Rel^d (w/o GT cam): 41.0 -> 32.7Improved
add AerialMegaDepth and MegaScenes to Stereo4D training (ablation)WildMoGe · 10 standard benchmarks (subset ablation)metric depth Rel^d (w/o GT cam): 19.0 -> 15.6Improved
use Stereo4D data in training (ablation)WildMoGe · 10 standard benchmarks (subset ablation)boundary F1: 14.5 -> 15.6Improved
use two-stage edge-aware Poisson completion instead of single-stage BG only (ablation)depth completion · MetricScenes test set depth labelsforeground person height: 3.26m tall person (BG only)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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