atlas

Research map / 3D vision / Depth and stereo

Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction

CVPR 2016 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 26 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 view-specific CNN normal prediction and integrate predicted normals into depth mapsMVS initialization · DTU, 14 objectscompleteness: 14 %Helped
Add view-specific CNN normal prediction and integrate predicted normals into depth mapsMVS initialization · DTU, 14 objectsoverall quality: 11%Helped
Predict missing normals with a CNN trained on the same image's MVS normalsMVS normal maps · DTU, 14 objectsmean angular error: 11◦ -> 18◦Hurt
Predict missing normals with a CNN trained on the same image's MVS normalsMVS normal maps · DTU, 14 objectsmean-of-median angular error: 9◦ -> 16◦Hurt
Train one normal predictor for multiple views instead of an individual model per image (ablation)View-specific normal prediction · DTU scenesnormal prediction performanceHurt
Use a per-image model rather than one model for multiple views (ablation)Normal prediction · DTU scenesnormal prediction performanceHelped

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