AI Paper Atlas

Research map / Image generation / Editing and style transfer

AM-Adapter: Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild

Siyoon Jin, Jisu Nam, Jiyoung Kim, Dahyun Chung, Yeong-Seok Kim, Joonhyung Park, Heonjeong Chu, Seungryong Kim

ICCV 2025 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 1 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 augmented self-attention (ablation)ControlNeXt · BDD100K (segmentation-to-image)I_CLIP: 0.731 -> 0.815Improved
add augmented self-attention (ablation)ControlNeXt · BDD100K (segmentation-to-image)FID: 94.48 -> 78.13Improved
add joint fine-tuning of augmented self-attention (ablation)augmented self-attention · BDD100K (segmentation-to-image)I_CLIP: 0.815 -> 0.808Hurt
add joint fine-tuning of augmented self-attention (ablation)augmented self-attention · BDD100K (segmentation-to-image)FID: 78.13 -> 77.75No clear effect
add categorical matching cost (ablation)augmented self-attention · BDD100K (segmentation-to-image)FID: 78.13 -> 76.76Improved
add 4D-aggregated matching adapter trained in separate stage (ablation)augmented self-attention + categorical matching cost · BDD100K (segmentation-to-image)FID: 76.76 -> 75.89Improved
add 4D-aggregated matching adapter trained in separate stage (ablation)augmented self-attention + categorical matching cost · BDD100K (segmentation-to-image)Self-sim.: 0.043 -> 0.041Improved
replace key-value replacement (MasaCtrl) with augmented self-attention (ablation)ControlNeXt · BDD100K (segmentation-to-image)I_CLIP: 0.872 -> 0.815Hurt
add DreamMatcher (ablation)ControlNeXt · BDD100K (segmentation-to-image)I_CLIP: 0.731 -> 0.724No clear effect
add exemplar retrieval at inference (ablation)AM-Adapter · BDD100K (segmentation-to-image)I_CLIP: 0.741 -> 0.814Improved
add matching cost guidance at inference (ablation)AM-Adapter + retrieval · BDD100K (segmentation-to-image)FID: 77.15 -> 75.89Improved
add exemplar retrieval at inference (ablation)AM-Adapter · BDD100K (segmentation-to-image)FID: 79.05 -> 77.15Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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