Metraipolis › archive › dc_d5b8a185d15c
SR-Edit: Region-Aware Image Editing via Self-Refinement — arXiv:2609.02504
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02504
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:50:07.475Z
- SHA-256 of the archived text
8d019d1cabc9c45f763764151e53cf1dc13b0f3e1d63ea0224b3ce7151792389- Stable URL of this page
https://metraipolis.com/documento/dc_d5b8a185d15c
How to cite
SR-Edit: Region-Aware Image Editing via Self-Refinement — arXiv:2609.02504 — arXiv (en), https://arxiv.org/abs/2609.02504 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5b8a185d15c (Metraipolis archive dc_d5b8a185d15c, sha256 8d019d1cabc9c45f763764151e53cf1dc13b0f3e1d63ea0224b3ce7151792389)
BibTeX
@misc{dcd5b8a185d15c,
title = {SR-Edit: Region-Aware Image Editing via Self-Refinement — arXiv:2609.02504},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02504},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5b8a185d15c; sha256 8d019d1cabc9c45f763764151e53cf1dc13b0f3e1d63ea0224b3ce7151792389},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02504. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
With the recent rapid progress in generative models, image editing has made remarkable advances, yet achieving faithful edits that precisely modify only the target regions while strictly preserving all other regions remains challenging. Since externally provided region annotations are often difficult to obtain in practice, a growing body of work seeks to improve preservation by automatically inferring edit and non-edit regions, and then enforcing consistency on the latter. However, these approaches still suffer from inaccurate region estimation and heuristic correction strategies that distort the native inference process, making methods designed for fidelity themselves a new source of artifacts. We propose SR-Edit, an image editing framework that overcomes these issues via iterative self-refinement. Specifically, at each iteration, SR-Edit first (i) extracts progressively precise and self-consistent region separation from the model's own predictions by lightweight post-processing, and then (ii) enforces preservation in non-edit areas through correction updates that remain aligned with the original sampling dynamics. Extensive experiments demonstrate that SR-Edit achieves superior preservation and overall image quality compared to existing editing techniques. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02504 — 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 2026-10-17T05:25:58.127Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).