AI Paper Atlas

Research map / Image generation / Editing and style transfer

GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation

Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy

TPAMI 2023 · Image generation › Editing and style transfer · approach: Image-to-image translation · 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 generative prior distillation for the content encoder (ablation)GP-UNIT · Ablation test setFID: 16.11 -> 15.29Improved
add generative prior distillation for the content encoder (ablation)GP-UNIT · Ablation user studycontent consistency: 0.02 -> 0.83Improved
add dynamic skip connection (ablation)GP-UNIT · Ablation test setFID: 15.83 -> 15.29Improved
add dynamic skip connection (ablation)GP-UNIT · Ablation user studycontent consistency: 0.15 -> 0.83Improved
add generative prior distillation (ablation)GP-UNIT · Ablation test setDiversity: 0.55 -> 0.51Hurt
add dynamic skip connection (ablation)GP-UNIT · Ablation test setDiversity: 0.52 -> 0.51Hurt
use 4 labeled pairs of semi-supervision (ablation)GP-UNIT · Bird<->Car layout consistencyaccuracy: 0.160 -> 0.895Improved
increase labeled pairs from 4 to 40 (ablation)GP-UNIT · Bird<->Car layout consistencyaccuracy: 0.895 -> 0.960Improved
use position loss L_pos instead of L2 on label maps (40 labeled) (ablation)GP-UNIT · Bird<->Car layout consistencyaccuracy: 0.245 -> 0.960Improved
semi-supervision with labeled pairs (user study) (ablation)GP-UNIT · Bird/Car user studyconsistent results: 17.3% -> 69.0%Improved
raise content control l from 0 to 1 (ablation)GP-UNIT · Dog <-> Catstyle loss and content loss: style 0.124 -> 0.109; content 0.845 -> 1.192Mixed
raise content control l from 0 to 1 (ablation)GP-UNIT · Male <-> Femalestyle loss: 0.146 -> 0.145No clear effect

Later papers that compared with this method

1 later accepted paper reports GP-UNIT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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