Research map / Image generation / Editing and style transfer
RegionRoute: Regional Style Transfer with Diffusion Model
Bowen Chen, Jake Zuena, Alan C. Bovik, Divya Kothandaraman
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add cover loss (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.2174 -> 0.2103 | Improved |
| add focus loss (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.2132 -> 0.2103 | Improved |
| add cover loss (ablation) | RegionRoute · Pascal VOC | MSE_bg: 0.0359 -> 0.0269 | Improved |
| add focus loss (ablation) | RegionRoute · BIG | MSE_bg: 0.0542 -> 0.0474 | Improved |
| add LoRA on double-stream blocks (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.4225 -> 0.2103 | Improved |
| add LoRA on single-stream blocks (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.5203 -> 0.2103 | Improved |
| add LoRA on double-stream blocks (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | RSM: 0.6168 -> 0.6128 | Hurt |
| add LoRA on single-stream blocks (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | RSM: 0.6190 -> 0.6128 | Hurt |
| increase LoRA rank from 4 to 8 (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.2103 -> 0.2007 | Improved |
| increase LoRA rank from 4 to 16 (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.2103 -> 0.1876 | Improved |
| increase LoRA rank from 4 to 16 (ablation) | RegionRoute · COCO (Grounded COCO, held-out) | RSM: 0.6128 -> 0.6126 | No clear effect |
| apply attention supervision and LoRA-MoE to Flux.1-Kontext | Flux.1-Kontext · COCO (Grounded COCO, held-out) | LPIPS_bg: 0.4546 -> 0.2103 | Improved |
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.
- AnyEdit — AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025) · better on 2 of 2 shared results
- Instruct-Pix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 1 of 2 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
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.91)
- SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer (CVPR 2025 · similarity 0.88)
- CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer (NeurIPS 2026 · similarity 0.88)
- Z*: Zero-shot Style Transfer via Attention Reweighting (CVPR 2024 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.88)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.88)
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.
