AI Paper Atlas

Research map / Image generation / Editing and style transfer

Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking

Tomislav Dobrički, Byung-Woo Hong

ECCV 2026 · Image generation › Editing and style transfer · approach: Image-to-image translation · 0 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 dynamic per-step masks instead of constant mask M_0.5T (ablation)PM-Edit · AFHQ Wild->DogLPIPS: 0.309 -> 0.445 (LPIPS), 33.3 -> 17.2 (KID)Mixed
use dynamic per-step masks instead of constant final mask M_0 (ablation)PM-Edit · AFHQ Wild->DogLPIPS: 0.533 -> 0.445Improved
use time-dependent threshold instead of constant delta_t (ablation)PM-Edit · AFHQ Wild->DogLPIPS: 0.698 -> 0.445Improved
average discrepancy over N=10 batches instead of N=1 (ablation)PM-Edit · AFHQ Wild->DogLPIPS: 0.617 -> 0.445Improved
add RePaint inpainting (ablation)PM-Edit · AFHQ Wild->DogKID: 28.0 -> 17.2Improved
raise threshold coefficient lambda from 1.0 to 1.8 (ablation)PM-Edit · AFHQ Wild->DogFID: FID 54.12 -> 62.89, SSIM 0.453 -> 0.531, LPIPS 0.459 -> 0.406Mixed
raise lambda from 1.2 to 1.4 (ablation)PM-Edit · AFHQ Wild->DogKID: 17.2 -> 19.4Hurt
use PM-Edit instead of CycleDiffusion (source-trained)translation · AFHQ Wild->DogKID: 19.5 -> 17.2Improved
use PM-Edit instead of CycleDiffusion on Cat->Dogtranslation · AFHQ Cat->DogFID: 58.87 -> 61.31Hurt
use PM-Edit instead of CycleDiffusion on Male->Femaletranslation · Celeba-HQ Male->FemaleFID: 45.04 -> 50.99Hurt
use PM-Edit instead of PnPInversionprompt editing · PIE-Benchstructure distance: 24.29 -> 19.68Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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