AI Paper Atlas

Research map / Image generation / Editing and style transfer

MIDMs: Matching Interleaved Diffusion Models for Exemplar-Based Image Translation

Junyoung Seo, Gyuseong Lee, Seokju Cho, Jiyoung Lee, Seungryong Kim

AAAI 2023 · Image generation › Editing and style transfer · approach: Image-to-image translation · 20 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
interleave recurrent cross-domain matching with diffusion denoising (ablation)MIDMs · CelebA-HQFID: 24.76 -> 15.67Improved
add confidence masking based on cycle consistency (ablation)MIDMs · CelebA-HQFID: 19.21 -> 15.67Improved
retain the diffusion U-Net (ablation)MIDMs · CelebA-HQFID: 128.70 -> 15.67Improved
use a 25% sampling noise level (ablation)MIDMs · CelebA-HQFID: 23.67 (20%) -> 15.67 (25%)Improved
add cycle-consistency loss (ablation)MIDMs · CelebA-HQFID: 16.18 -> 15.67Improved
add style loss (ablation)MIDMs · CelebA-HQFID: 19.23 -> 15.67Improved
add perceptual loss (ablation)MIDMs · CelebA-HQFID: 16.51 -> 15.67Improved
add domain loss (ablation)MIDMs · CelebA-HQFID: 16.68 -> 15.67Improved
add source loss (ablation)MIDMs · CelebA-HQFID: 72.25 -> 15.67Improved
increase sampling steps from T=16, N=4 to T=200, N=50 (ablation)MIDMs · CelebA-HQFID: 17.94 -> 15.67Improved
apply iterative matching and generation using a GAN-based generator (ablation)CoCosNet · DeepFashionFID: 14.4 -> 19.05Hurt
use MIDMs instead of MCL-Netexemplar-based translation · CelebA-HQ w/ sourcesFID: 12.52 -> 15.67Hurt

Later papers that compared with this method

1 later accepted paper reports MIDMs 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 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