Metraipolis › archive › dc_ea8300e7ed04
Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness — arXiv:2609.06602
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06602
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:09:13.896Z
- SHA-256 of the archived text
b65c41ec0730f57092b819edccab0a12eac3a97dafea44076c3fd8e5a84cd63a- Stable URL of this page
https://metraipolis.com/documento/dc_ea8300e7ed04
How to cite
Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness — arXiv:2609.06602 — arXiv (en), https://arxiv.org/abs/2609.06602 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea8300e7ed04 (Metraipolis archive dc_ea8300e7ed04, sha256 b65c41ec0730f57092b819edccab0a12eac3a97dafea44076c3fd8e5a84cd63a)
BibTeX
@misc{dcea8300e7ed04,
title = {Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awareness — arXiv:2609.06602},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06602},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea8300e7ed04; sha256 b65c41ec0730f57092b819edccab0a12eac3a97dafea44076c3fd8e5a84cd63a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06602. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In recent years, diffusion stochastic differential equation (SDE) inversion and inversion-free methods have become prevalent for training-free image editing, as they can achieve faithful reconstruction without tuning. However, existing approaches remain inefficient, exhibit limited plasticity, and struggle to accurately preserve unedited regions. To address these issues, we propose MIEdit, a training-free editing framework based on SDE inversion. MIEdit introduces a predictor-corrector multi-history-step scheme to achieve superior editing quality with fewer steps. We further mitigate heterogeneity and conflict between the multi-conditioned noise residuals and gradient terms during sampling, improving stability and editing plasticity under large edits. MIEdit also includes Inversion-Time Automatic Semantic Angle Masking (IASM); it leverages classifier-free guidance to automatically generate semantic angle masks during inversion and applies them throughout the sampling process for regional constraints, without extra user inputs. We additionally construct EditEval++ (30 fine-grained tasks, 1,000+ image-text-mask triplets) for comprehensive evaluation; experiments show that MIEdit outperforms state-of-the-art techniques. Project page: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.06602 — 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 2026-10-16T14:49:57.102Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).