AI Paper Atlas

Research map / 3D vision / Depth and stereo

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue

Ravi Garg, Vijay Kumar B.G., Gustavo Carneiro, Ian Reid

ECCV 2016 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 1,641 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 8x augmentation fine-tuning (color, scale, flips) (ablation)Ours L12 · KITTI (Eigen test split, 1-50m)RMS: 5.285 -> 5.104Improved
add 8x augmentation fine-tuning (ablation)Ours L12 · KITTI (Eigen test split, 1-50m)absolute relative error: 0.177 -> 0.169Improved
add 8x augmentation fine-tuning (ablation)Ours L12 · KITTI (Eigen test split, 1-50m)accuracy delta<1.25: 0.727 -> 0.740Improved
add third skip-connection at L10 (ablation)Ours L10 · KITTI (Eigen test split, 1-50m)RMS: 5.434 -> 5.850Hurt
add third skip-connection at L10 (ablation)Ours L10 · KITTI (Eigen test split, 1-50m)absolute relative error: 0.189 -> 0.246Hurt
increase output resolution from L10 to L12 via more upsampling layers (ablation)Ours · KITTI (Eigen test split, 1-50m)RMS: 5.434 -> 5.285Improved
increase output resolution from L9 to L10 (ablation)Ours · KITTI (Eigen test split, 1-50m)RMS: 5.740 -> 5.434Improved
train with photometric reconstruction loss instead of supervising on Horn-Schunck stereo output (ablation)CNN · KITTI (Eigen test split, 1-50m)RMS: 6.292 -> 5.285Improved
train with photometric loss instead of supervising on SGM stereo output (ablation)CNN · KITTI (Eigen test split, 1-50m)RMS: 5.680 -> 5.285Improved
train with photometric loss instead of HS->CNN with gamma=.01 (ablation)CNN · KITTI (Eigen test split, 1-50m)accuracy delta<1.25: 0.476 -> 0.727Improved
use lower regularization gamma=0.01 for HS->CNN stereo supervision (ablation)HS->CNN · KITTI (stereo baseline comparison)RMS: 6.292 -> 6.691Hurt
unsupervised photometric training vs supervised Eigen et al fineOurs L12 · KITTI (Eigen test split, 1-50m)RMS: 7.156 -> 5.285Improved

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