AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Perspective Undistortion of Portraits

Yajie Zhao, Zeng Huang, Tianye Li, Weikai Chen, Chloe LeGendre, Xinglei Ren, Ari Shapiro, Hao Li

ICCV 2019 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 27 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
replace Fried et al. with learned cascade undistortionportrait undistortion · BU-4DFE synthetic pairsaverage intensity error: 1.28 -> 0.39Improved
add FlowNet before CompletionNet (cascade) vs single image-to-image network (ablation)portrait undistortion · qualitative ablationimage sharpnessImproved
add distance label channel as input to FlowNet (ablation)FlowNet · qualitative ablationdistortion of nose, mouth, face rimImproved
undistort near-range portrait before face verificationOpenFace · BU-4DFE face verificationaccuracy: 0.9137 -> 0.9473Improved
undistort portrait before landmark detectionOpenPose · BU-4DFE renderingsdetection failure rate: 9.0% -> 0%Improved
undistort portrait before landmark detectionOpenPose · BU-4DFE renderingsNME: 4.9% -> 4.4%Improved
undistort portrait before 3D face reconstructionFaceWarehouse fitting · near-range portraitsreconstruction errorImproved

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