AI Paper Atlas

Research map / Image generation / Editing and style transfer

Dual Diffusion Implicit Bridges for Image-to-Image Translation

Xuan Su, Jiaming Song, Chenlin Meng, Stefano Ermon

ICLR 2023 · Image generation › Editing and style transfer · approach: Image-to-image translation · 13 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
Use DDIBs instead of CycleGANFacades A → B translation · Facades paired testMSE: 0.7129 -> 0.5312Improved
Use DDIBs instead of AlignFlowFacades A → B translation · Facades paired testMSE: 0.5801 -> 0.5312Improved
Use DDIBs instead of AlignFlowFacades B → A translation · Facades paired testMSE: 0.2512 -> 0.3946Hurt
Use DDIBs instead of CycleGANMaps A → B translation · Maps paired testMSE: 0.0245 -> 0.0194Improved
Use DDIBs instead of AlignFlowMaps A → B translation · Maps paired testMSE: 0.0209 -> 0.0194Improved
Use DDIBs instead of CycleGANMaps B → A translation · Maps paired testMSE: 0.0953 -> 0.1302Hurt
Use DDIBs instead of AlignFlowMaps B → A translation · Maps paired testMSE: 0.0897 -> 0.1302Hurt
Translate between domains with DDIBs' reversible ODE mappingsDDIBs · 2D synthetic datasetsL2 cycle distance: 0.0143, 0.0065, 0.0106, 0.0078, 0.0122Improved

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