AI Paper Atlas

Research map / Image generation / Editing and style transfer

Multimodal Unsupervised Image-to-image Translation

Xun Huang, Ming-Yu Liu, Serge Belongie, Jan Kautz

ECCV 2018 · Image generation › Editing and style transfer · approach: Image-to-image translation · 2,725 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 image reconstruction loss (ablation)MUNIT · edges->shoeshuman preference over MUNIT (%): 6.0% -> 50.0%Improved
add content reconstruction loss (ablation)MUNIT · edges->handbagshuman preference over MUNIT (%): 9.3% -> 50.0%Improved
add style reconstruction loss (ablation)MUNIT · edges->shoesLPIPS diversity: 0.070 -> 0.109Improved
add style reconstruction loss (ablation)MUNIT · edges->handbagsLPIPS diversity: 0.139 -> 0.175Improved
add style reconstruction loss (ablation)MUNIT · edges->shoeshuman preference over MUNIT (%): 28.6% -> 50.0%Improved
inject noise vectors into CycleGANCycleGAN · edges->shoesLPIPS diversity: 0.010 -> 0.016No clear effect
inject noise vectors into CycleGANCycleGAN · edges->shoeshuman preference over MUNIT (%): 36.0% -> 29.5%Hurt
inject noise vectors into CycleGANCycleGAN · edges->handbagshuman preference over MUNIT (%): 40.8% -> 45.1%Improved
use MUNIT instead of UNITUNIT · Animal image translation (average of 6 tasks)CIS: 0.115 -> 1.039Improved
use MUNIT instead of CycleGANCycleGAN · Animal image translation (average of 6 tasks)IS: 0.813 -> 1.050Improved
train MUNIT unsupervised instead of BicycleGAN with paired supervisionBicycleGAN · edges->shoeshuman preference over MUNIT (%): 56.7% -> 50.0%No clear effect
apply Instance Normalization to VGG features in the perceptual loss (ablation)MUNIT perceptual loss · day/night image pairsVGG feature distance domain invarianceImproved

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