arXiv cs.AI· Sara Dorfman, Nir Goren, Gal Barak, Daniel Cohen-Or, Or Patashnik·· 2 天前AI 评分24
ACEdit：用非对称条件化实现稳定的多轮图像编辑
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
AI 导读
ACEdit 提出一种训练方案，让图像编辑模型在多轮编辑中保持稳定：训练时强制编辑器处理自己前几轮的输出，把 Self-Forcing 引入图像编辑。由于自生成轨迹偏离真值、直接监督不可靠，该方法用蒸馏目标让教师编辑器提供可靠信号，并采用非对称条件化——学生基于自身输出顺序编辑，教师始终锚定原始干净图像并接收复合编辑指令。实验显示长多轮序列中的质量退化显著降低，同时保持编辑质量与指令遵循。
正文 · 原文
Abstract:Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribution shifts that accumulate over successive edits, creating a gap between the input distributions encountered during the editor's original training and multi-turn inference. We introduce a training scheme that makes multi-turn image editing stable under this accumulating distribution shift. A key is to force the editor to operate on its own outputs from previous editing turns during training, bringing the principle of Self-Forcing to image editing. The main challenge is that self-generated editing trajectories deviate from ground-truth trajectories, making direct supervision unreliable. We address this challenge through a distillation objective that leverages a teacher image editor to provide a reliable training signal when the model operates on its own previous outputs. We introduce an asymmetric conditioning scheme: while the student performs edits sequentially on its own outputs, the teacher remains anchored to the original clean image and receives a compound editing instruction. Experiments show substantially reduced degradation over long multi-turn sequences while maintaining editing quality and instruction adherence.
| Comments: | Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR) |
| Cite as: | arXiv:2610.22328 [cs.CV] |
| (or arXiv:2610.22328v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22328 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sara Dorfman [view email]
[v1]
Thu, 15 Oct 2026 17:52:24 UTC (21,992 KB)
来源：arXiv cs.AI · arxiv.org