AI Paper Atlas

Research map / 3D vision / Depth and stereo

Digging Into Self-Supervised Monocular Depth Estimation

Clement Godard, Oisin Mac Aodha, Michael Firman, Gabriel J. Brostow

ICCV 2019 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 2,691 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
add minimum reprojection loss (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.117 -> 0.115Improved
add auto-masking (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.120 -> 0.115Improved
add full-resolution multi-scale sampling (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.117 -> 0.115Improved
add minimum reprojection loss to baseline (ablation)Baseline · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.140 -> 0.122Improved
add auto-masking to baseline (ablation)Baseline · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.140 -> 0.124Improved
add full-res multi-scale to baseline (ablation)Baseline · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.140 -> 0.124Improved
replace auto-masking with predictive mask (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.115 -> 0.123Hurt
add SSIM to photometric loss (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.118 -> 0.115Improved
add ImageNet pretraining (ablation)Monodepth2 · KITTI Eigen split, monocularAbs Rel: 0.132 -> 0.115Improved
add all three contributions without pretraining (ablation)Baseline w/o pt · KITTI Eigen split, monocular, from scratchAbs Rel: 0.150 -> 0.132Improved
train on full Eigen split with Monodepth2 components (ablation)Baseline · KITTI full Eigen split, monocularAbs Rel: 0.146 -> 0.116Improved
increase input resolution from 416x128 to 640x192 (ablation)Monodepth2 · KITTI Eigen split, monocular, pretrainedAbs Rel: 0.128 -> 0.115Improved

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