AI Paper Atlas

Research map / 3D vision / Depth and stereo

LumiDepth: Stable Monocular Depth in Multi-Illumination Scenes

Anqi Cheng, Zhiyuan Yang, Tianjiao Li, Haiyue Zhu, Kezhi Mao

ECCV 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 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
DCPS probabilistic selection instead of best/mean/median (ablation)LumiDepth · ReMIDAbsRel: 0.088 (Best) -> 0.085Improved
DCPS instead of Best selection (ablation)LumiDepth · NuScenes-NightAbsRel: 0.245 -> 0.223Improved
FaCD instead of naive latent consistency (ablation)LumiDepth n-step · ReMIDAbsRel: 0.365 -> 0.138Improved
FaCD (LF+HF) instead of LF only (ablation)LumiDepth n-step · ReMIDAbsRel: 0.145 -> 0.138Improved
add pseudo loss (DCPS pseudo labels) (ablation)LumiDepth · ReMIDMeanDV: 0.035 -> 0.030Improved
add frequency consistency terms (ablation)LumiDepth · ReMIDMeanDV: 0.042 -> 0.030Improved
add GT depth loss (ablation)LumiDepth · ReMIDAbsRel: MeanDV 0.029 -> 0.030; AbsRel 0.092 -> 0.085; NuScenes AbsRel 0.264 -> 0.223Mixed
plug DCPS+FaCD into discriminative DAv2 (ablation)DAv2 · ReMIDMeanDV / AbsRel: 0.051 -> 0.036; 0.119 -> 0.102Improved
naive self-training on 14K RGB-only data (no DCPS/FaCD) (ablation)Lotus · NYUv2AbsRel: 0.054 -> 0.057Hurt
LumiDepth training on multi-illumination RGB dataLotus · ReMIDAbsRel: 0.113 -> 0.085Improved
LumiDepth trainingLotus · NYUv2AbsRel: 0.054 -> 0.052Improved
LumiDepth trainingLotus · RoboDepthMeanDV: 0.051 -> 0.038Improved

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