Metraipolis › archive › dc_4d020552c761
Constrained Edit Fields for Training-Free Flow Editing — arXiv:2609.33735
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33735
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:40:09.268Z
- SHA-256 of the archived text
2bf93c83fb21ca24003146b39891e49fb9ff0696eb493131f3923fa19a6c7d9a- Stable URL of this page
https://metraipolis.com/documento/dc_4d020552c761
How to cite
Constrained Edit Fields for Training-Free Flow Editing — arXiv:2609.33735 — arXiv (en), https://arxiv.org/abs/2609.33735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d020552c761 (Metraipolis archive dc_4d020552c761, sha256 2bf93c83fb21ca24003146b39891e49fb9ff0696eb493131f3923fa19a6c7d9a)
BibTeX
@misc{dc4d020552c761,
title = {Constrained Edit Fields for Training-Free Flow Editing — arXiv:2609.33735},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33735},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d020552c761; sha256 2bf93c83fb21ca24003146b39891e49fb9ff0696eb493131f3923fa19a6c7d9a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-guided image editing aims to perform a desired edit while preserving source content unrelated to it. Pretrained rectified-flow models enable training-free editing of real images through modifications to their sampling trajectories. However, responses at locations unrelated to the desired edit can still accumulate along the editing trajectory and become visible in the final result. To overcome this, we propose Constrained Edit Fields (CEF), which assigns each spatial location a continuous edit responsibility that quantifies its relevance to the desired edit. CEF estimates edit responsibility directly from the source image when the relevant content is present. For edits whose target content is absent from the source, CEF first generates an unconstrained proposal to reveal its realized spatial support and then estimates responsibility from that proposal. At each editing step, CEF decomposes the base edit field into prompt-induced and trajectory-induced components, enabling edit responsibility to preserve instruction-relevant updates while suppressing unintended trajectory-induced changes. Evaluated on all 700 PIE-Bench examples, CEF achieves state-of-the-art Structure Distance, background LPIPS, and background MSE with both Stable Diffusion 3.5 Medium and FLUX, while retaining competitive instruction alignment. On Stable Diffusion 3.5 Medium, it reduces these metrics over the previous best results by 10.2%, 21.2%, and 48.0%, respectively. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33735 — 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 2026-10-07T22:14:28.759Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).