AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Single-Image Depth From Videos Using Quality Assessment Networks

Weifeng Chen, Shengyi Qian, Jia Deng

CVPR 2019 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 69 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
Filter SfM video reconstructions with QANet to form YouTube3DHourglass depth network · DIW testWHDR: 25.11% -> 19.01%Improved
Add YouTube3D training dataHourglass trained on NYU + DIW · DIW testWHDR: 14.39% -> 13.50%Improved
Add YouTube3D training dataEncDecResNet (our implementation) trained on ImageNet + ReDWeb + DIW · DIW testWHDR: 12.03% -> 10.59%Improved
Train on YouTube3D instead of DIW training dataHourglass depth network · DIW testWHDR: 22.14% -> 19.01%Improved
Add QA_train to NYU training dataHourglass depth network · DIW testWHDR: 31.31% -> 31.22%No clear effect
Add the 2D coordinate feature to QANet (ablation)Full QANet · NYU Depth testAUC: 80.53% -> 83.56%Improved
Add the 2D coordinate feature to QANet (ablation)Full QANet · FlyingThings3D testAUC: 85.34% -> 89.02%Improved
Add Sampson distance feature to QANet (ablation)Full QANet · NYU Depth testAUC: 83.20% -> 83.56%Improved
Add Sampson distance feature to QANet (ablation)Full QANet · FlyingThings3D testAUC: 88.66% -> 89.02%Improved
Add angle feature to QANet (ablation)Full QANet · NYU Depth testAUC: 82.09% -> 83.56%Improved
Add angle feature to QANet (ablation)Full QANet · FlyingThings3D testAUC: 85.00% -> 89.02%Improved
Add focal length feature to QANet (ablation)Full QANet · NYU Depth testAUC: 82.54% -> 83.56%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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