atlas

Research map / 3D vision / Depth and stereo

Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge

CVPR 2019 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 233 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Add SGM proxy supervision (ablation)monoResMatch · KITTI Eigen split (K)Abs Rel: 0.116 -> 0.111Helped
Add the disparity refinement module (ablation)monoResMatch · KITTI Eigen split (CS,K)Abs Rel: 0.107 -> 0.096Helped
Add correlation-based matching to refinement (ablation)monoResMatch · KITTI Eigen split (CS,K)Abs Rel: 0.104 -> 0.098Helped
Add disparity refinement without matching correlation (ablation)monoResMatch · KITTI Eigen split (CS,K)Abs Rel: 0.107 -> 0.104Helped
Add test-time post-processing (ablation)monoResMatch · KITTI Eigen split (CS,K)Abs Rel: 0.098 -> 0.096Helped
Pretrain on CityScapes before KITTI training (ablation)monoResMatch · KITTI Eigen split, max depth 80mAbs Rel: 0.116 -> 0.096Helped
Use monoResMatch instead of SVSKITTI 2015 Stereo Benchmark · KITTI 2015 Stereo Benchmark testD1-all: 24.44 -> 21.72Helped

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