AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation

Wenzhuang Wang, Yifan Zhao, Mingcan Ma, Ming Liu, Zhonglin Jiang, Yong Chen, Jia Li

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 6 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 FPR (frequency perceiver resampler) (ablation)FICGen with VFEA + ASFA · DIOR (ablation, Faster R-CNN R50)mAP: 25.6 -> 27.6Improved
add ASFA (adaptive spatial-frequency aggregation) (ablation)FICGen with FPR + VFEA · DIOR (ablation, Faster R-CNN R50)mAP: 25.5 -> 27.6Improved
add VFEA (visual-frequency enhanced attention) (ablation)base L2I model · DIOR (ablation, Faster R-CNN R50)mAP: 15.7 -> 23.2Improved
add VFEA to FPR + ASFA (ablation)FPR + ASFA · DIOR (ablation, Faster R-CNN R50)mAP: 18.5 -> 27.6Improved
add FPR and ASFA on top of VFEA (ablation)VFEA only · DIOR (ablation, Faster R-CNN R50)mAP: 23.2 -> 27.6Improved
replace CC-Diff by FICGen for layout-to-image generationCC-Diff · DIOR-H (Faster R-CNN)mAP: 23.6 -> 27.6Improved
replace CC-Diff by FICGenCC-Diff · RUOD (Faster R-CNN)mAP: 29.7 -> 37.0Improved
replace CC-Diff by FICGenCC-Diff · DAWN (Cascade R-CNN)mAP: 15.7 -> 22.6Improved
replace CC-Diff by FICGenCC-Diff · DIOR-H (Faster R-CNN)FID: 30.88 -> 31.25Mixed
replace AeroGen by FICGenAeroGen · DIOR-H (YOLOv8)mAP: 29.8 -> 31.2Improved
mix FICGen synthetic data with real data, fine-tuning on real after synthetic pretrainingFaster R-CNN X101 on ExDARK · ExDARK trainabilitymAP: 38.6 -> 40.6Improved
train on pure FICGen synthetic data instead of real dataFaster R-CNN X101 on ExDARK · ExDARK trainabilitymAP: 38.6 -> 26.7Hurt

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