AI Paper Atlas

Research map / Image generation / Editing and style transfer

RegionRoute: Regional Style Transfer with Diffusion Model

Bowen Chen, Jake Zuena, Alan C. Bovik, Divya Kothandaraman

CVPR 2026 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 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
add cover loss (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.2174 -> 0.2103Improved
add focus loss (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.2132 -> 0.2103Improved
add cover loss (ablation)RegionRoute · Pascal VOCMSE_bg: 0.0359 -> 0.0269Improved
add focus loss (ablation)RegionRoute · BIGMSE_bg: 0.0542 -> 0.0474Improved
add LoRA on double-stream blocks (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.4225 -> 0.2103Improved
add LoRA on single-stream blocks (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.5203 -> 0.2103Improved
add LoRA on double-stream blocks (ablation)RegionRoute · COCO (Grounded COCO, held-out)RSM: 0.6168 -> 0.6128Hurt
add LoRA on single-stream blocks (ablation)RegionRoute · COCO (Grounded COCO, held-out)RSM: 0.6190 -> 0.6128Hurt
increase LoRA rank from 4 to 8 (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.2103 -> 0.2007Improved
increase LoRA rank from 4 to 16 (ablation)RegionRoute · COCO (Grounded COCO, held-out)LPIPS_bg: 0.2103 -> 0.1876Improved
increase LoRA rank from 4 to 16 (ablation)RegionRoute · COCO (Grounded COCO, held-out)RSM: 0.6128 -> 0.6126No clear effect
apply attention supervision and LoRA-MoE to Flux.1-KontextFlux.1-Kontext · COCO (Grounded COCO, held-out)LPIPS_bg: 0.4546 -> 0.2103Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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