AI Paper Atlas

Research map / 3D vision / Depth and stereo

Monocular Depth Estimation Using Relative Depth Maps

Jae-Han Lee, Chang-Su Kim

CVPR 2019 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 144 citations (OpenAlex)

Check 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
estimate and combine relative depth maps with ordinary depth maps (ablation)Proposed monocular depth estimation method · NYUv2 testSpearman's ρ: 0.885 -> 0.914Improved
add relative depth maps R3, R4, R5, and R6 to D3 (ablation)Proposed method · NYUv2 testRMSE (lin): 0.583 -> 0.538Improved
add relative depth maps R3, R4, R5, and R6 to D3 (ablation)Proposed method · NYUv2 testARD: 0.143 -> 0.131Improved
use a higher-resolution ordinary depth map instead of D3 alone (ablation)Ordinary-depth-only variant · NYUv2 testRMSE (lin): 0.583 -> 0.552Improved
add ordinary depth maps D4 through D7 to D3 and R3 through R7 (ablation)Proposed method · NYUv2 testSpearman's ρ: 0.914 -> 0.912Hurt
add R7 to D3, R3, R4, R5, and R6 (ablation)Proposed method · NYUv2 testRMSE (lin): 0.538 -> 0.538No clear effect
add relative depth maps to D3 (ablation)Proposed method · NYUv2 testRMSE (lin): 0.550 -> 0.538Improved

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