AI Paper Atlas

Research map / Image generation / Editing and style transfer

Quality Metric Guided Portrait Line Drawing Generation From Unpaired Training Data

Ran Yi, Yong‐Jin Liu, Yu-Kun Lai, Paul L. Rosin

TPAMI 2022 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 26 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 relaxed cycle-consistency loss and local discriminators (ablation)APDrawing generator · APDrawings, Style1 FIDFID: 102.9 -> 81.2Improved
add relaxed cycle-consistency loss (ablation)APDrawing generator · APDrawings, Style1 FIDFID: 88.0 -> 81.2Improved
add local discriminators (ablation)APDrawing generator · APDrawings, Style2 FIDFID: 142.3 -> 114.3Improved
add HED edge extraction in relaxed cycle loss (ablation)APDrawing generator · APDrawings, Style3 FIDFID: 103.4 -> 89.7Improved
add quality loss from quality metric model (ablation)APDrawing generator · APDrawings, Style3 FIDFID: 108.2 -> 89.7Improved
add style feature vector and style loss (ablation)APDrawing generator · APDrawings, Style1 FIDFID: 114.3 -> 81.2Improved
add truncation loss (ablation)APDrawing generator · APDrawings, Style1 FIDFID: 81.7 -> 81.2Improved
use local discriminators instead of single discriminator with face-region channel (ablation)APDrawing generator · APDrawings, Style2 FIDFID: 152.8 -> 114.3Improved
use full method instead of conference version (Ours-pre, no relaxed/local/style improvements)APDrawing generator · APDrawings, Style3 FIDFID: 108.2 -> 89.7Improved
use full method instead of DRITAPDrawing generator · APDrawings, Style2 FIDFID: 135.0 -> 114.3Improved
use full method instead of ComboGAN in user study (ranked first)APDrawing generator · User studypercentage ranked first: 23.7% -> 45.1%Improved
use full method instead of Ours-pre on quality metric scoreAPDrawing generator · APDrawings test setQuality score: 0.45 -> 0.51Improved

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