AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

PPR10K: A Large-Scale Portrait Photo Retouching Dataset With Human-Region Mask and Group-Level Consistency

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 55 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 human-region-prioritized loss (ablation)3D LUT · PPR10K-a, PPR10K-b, and PPR10K-c (HR)PSNRHC: 28.39 -> 28.83; 27.59 -> 27.93; 28.09 -> 28.38Helped
Add group-level consistency loss (ablation)3D LUT · PPR10K-a (HR)MGLC: 11.05 -> 9.77Helped
Add group-level consistency loss (ablation)3D LUT · PPR10K-a (HR)PSNR: 25.15 -> 24.39Hurt
Add both human-region-prioritized and group-level consistency losses (ablation)3D LUT · PPR10K-a and PPR10K-b (HR)MGLC: 11.05 -> 9.68; 9.52 -> 8.73Helped
Train on PPR10K rather than FiveK3D LUT, HDRNet, and CSRNet · PPR10K test setsPSNRHelped

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