AI Paper Atlas

Research map / Image generation / Editing and style transfer

Improving Shape Deformation in Unsupervised Image-to-Image Translation

Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin

ECCV 2018 · Image generation › Editing and style transfer · approach: Image-to-image translation · 78 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 dilated discriminator instead of patch discriminator (ablation)GANimorph · Cat->Dogtarget class pixels (%): 42.90 -> 98.57Improved
add dilated discriminator instead of patch discriminator (ablation)GANimorph · Dog->Cattarget class pixels (%): 91.77 -> 100.00Improved
add dilated discriminator instead of fully connected discriminator (ablation)GANimorph · Cat->Dogtarget class pixels (%): 93.60 -> 98.57Improved
add dilated discriminator instead of fully connected discriminator (ablation)GANimorph · Dog->Cattarget class pixels (%): 91.41 -> 100.00Improved
add feature matching loss (ablation)GANimorph · Cat->Dogtarget class pixels (%): 93.64 -> 98.57Improved
add feature matching loss (ablation)GANimorph · Dog->Cattarget class pixels (%): 85.62 -> 100.00Improved
add MS-SSIM perceptual cyclic loss instead of L1 only (ablation)GANimorph · Cat->Dogtarget class pixels (%): 0.00 -> 98.57Improved
add MS-SSIM perceptual cyclic loss instead of L1 only (ablation)GANimorph · Dog->Cattarget class pixels (%): 0.00 -> 100.00Improved
use GANimorph generator with fully connected discriminator instead of DiscoGANDiscoGAN · Cat->Dogtarget class pixels (%): 75.38 -> 93.60Improved
use GANimorph instead of CycleGANCycleGAN · Cat->Dogtarget class pixels (%): 0.01 -> 98.57Improved

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