Metraipolis › archive › dc_be17e8160eea
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network — arXiv:2609.20633
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20633
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:08:00.226Z
- SHA-256 of the archived text
1c42422378a87d419e8b5cd4abc51826344dc13c0331988a134603e230ed91b4- Stable URL of this page
https://metraipolis.com/documento/dc_be17e8160eea
How to cite
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network — arXiv:2609.20633 — arXiv (en), https://arxiv.org/abs/2609.20633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be17e8160eea (Metraipolis archive dc_be17e8160eea, sha256 1c42422378a87d419e8b5cd4abc51826344dc13c0331988a134603e230ed91b4)
BibTeX
@misc{dcbe17e8160eea,
title = {Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network — arXiv:2609.20633},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20633},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be17e8160eea; sha256 1c42422378a87d419e8b5cd4abc51826344dc13c0331988a134603e230ed91b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-guided image editing must introduce the requested changes while preserving unrelated source content. In training-free editing, diffusion editors often use spatial controls whose inaccuracies can leave edits incomplete or alter unrelated regions. Causal autoregressive editors face a further constraint: their fixed decoding order limits revision of earlier decisions. As the first to explore training-free image editing with Generative Refinement Networks (GRN), we observe that its refinement process is inherently suitable for editing and offers a promising way to address these limitations. Motivated by this observation, we introduce RefineEdit, a training-free prompt-to-prompt image editing framework built on the GRN. Our key idea is to couple edit localization with content generation through the global refinement of binary image codes, allowing editing evidence to be revised as the image evolves. More specifically, RefineEdit combines bit routing with two stabilization mechanisms: adaptive spatial freezing and finite bit locking. Bit routing starts from an intermediate source state and uses signed probability differences between the two branches to identify editable positions and bits. It directs selected bits toward editing refinement while anchoring the rest to the evolving source trajectory. Adaptive spatial freezing limits unnecessary expansion of the editing region, while finite bit locking maintains recent bit activations to support continued editing. The overall framework requires no additional training, external masks, or attention control. Across nine editing categories of PIE-Bench, RefineEdit achieves the best background-preservation scores in PSNR, LPIPS, MSE, and SSIM, together with the highest whole-image and edited-region CLIP scores among the evaluated methods. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.20633 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T04:26:09.619Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).