AI Paper Atlas

Research map / 3D vision / Depth and stereo

MegaDepth: Learning Single-View Depth Prediction From Internet Photos

Zhengqi Li, Noah Snavely

CVPR 2018 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 1,151 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 multi-scale gradient matching loss (ablation)MegaDepth depth predictor · MegaDepth testsi-RMSE: 0.148 -> 0.123Improved
Add multi-scale gradient matching loss (ablation)MegaDepth depth predictor · MegaDepth testSDR %: 31.75 -> 27.11Improved
Add automatically labeled ordinal depth loss (ablation)MegaDepth depth predictor with L_data + L_grad · MegaDepth testsi-RMSE: 0.123 -> 0.104Improved
Add automatically labeled ordinal depth loss (ablation)MegaDepth depth predictor with L_data + L_grad · MegaDepth testSDR %: 27.11 -> 25.82Improved
Add automatically labeled ordinal depth loss (ablation)MegaDepth depth predictor with L_data + L_grad · MegaDepth testSDR=: 26.17 -> 27.73Hurt
Use refined and cleaned MVS depth maps instead of raw MVS depth maps (ablation)MegaDepth training data · Make3DRMS: 11.41 -> 5.322Improved
Use refined and cleaned MVS depth maps instead of raw MVS depth maps (ablation)MegaDepth training data · KITTIRMS: 12.15 -> 6.680Improved
Use refined and cleaned MVS depth maps instead of raw MVS depth maps (ablation)MegaDepth training data · DIWWHDR %: 31.32 -> 24.55Improved
Use an hourglass architecture instead of VGGMegaDepth depth predictor · MegaDepth testsi-RMSE: 0.115 -> 0.104Improved
Train on MegaDepth instead of Make3DSingle-view depth predictor · Make3DRMS: 4.45 -> 6.23Mixed
Train on MegaDepth instead of KITTISingle-view depth predictor · KITTIRMS: 5.93 -> 6.68Mixed
Train on MegaDepth instead of DIWSingle-view depth predictor · DIWWHDR %: 22.14 -> 24.55Hurt

Later papers that compared with this method

3 later accepted papers report MegaDepth as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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