← Back to all news
arXiv Computer Vision By Yulong Chen, Ziqian Zhang, Haoyu Zhang, Ao He, Senmao Li, Kai Wang

Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network

Read the original on arXiv Computer Vision →

RefineEdit is a training‑free prompt‑to‑prompt image editing framework that uses a Generative Refinement Network to edit images by refining binary image codes. It couples edit localization with content generation, selecting editable positions based on signed probability differences between an editing branch and a source branch, and stabilizes edits with adaptive spatial freezing and finite bit locking. The method requires no additional training, external masks, or attention control, and outperforms other methods on PIE‑Bench in background‑preservation metrics and CLIP scores.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Jul 23

PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing

Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content. Existing training-free editors either localize edits from terminal predictions under source and target prompts or preserve unrelated content through spatially unselective source-feature reuse without explicit region discovery.

More like this →
arXiv Computer Vision
Sep 3

SR-Edit: Region-Aware Image Editing via Self-Refinement

SR-Edit is a new image editing framework that uses iterative self‑refinement to improve fidelity. At each step it extracts precise, self‑consistent region separations from the model’s predictions and then enforces preservation in non‑edit areas with correction updates that stay aligned with the original sampling dynamics. Experiments show that SR‑Edit delivers better preservation and overall image quality than existing editing techniques.

By Andong Wang, Zehua Chen, Yuxuan Jiang, Jun Zhu
More like this →
arXiv Computer Vision
Sep 4

Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing

The paper introduces RC‑GRPO‑Editing, a region‑constrained Group Relative Policy Optimization framework for flow‑based image editing. It localizes exploration by decoupling initial noise perturbations to reduce background‑induced reward variance and adds an attention concentration reward to keep cross‑attention focused on the intended editing region. Experiments on CompBench demonstrate consistent gains in instruction adherence within the editing region while better preserving non‑target content.

By Zhuohan Ouyang, Zhe Qian, Wenhuo Cui, Chaoqun Wang
More like this →