Aug 2026· International Conference on Multimedia Analysis and Pattern Recognition· pp. 574-579· 0 citations· 21 references
Abstract
Text-guided image editing using rectified flow models such as Multimodal Diffusion Transformer (DiT) has demonstrated impressive generation quality. However, existing methods apply edits globally, inevitably modifying background regions unrelated to the intended semantic change. Our key observation is that the Text-to-Image (T2I) sub-block within the MM-DiT joint self-attention naturally encodes highly discriminative spatial localization signals. In this paper, we propose MaskFlow, a training-free framework for spatially localized image editing in rectified flow models. By strategically extracting and aggregating these attention maps from edit-relevant tokens during the standard ODE forward passes, MaskFlow automatically constructs a soft spatial mask. This mask confines semantic edits to the target region while perfectly preserving the original background. MaskFlow operates as a lightweight, plug-and-play extension without retraining the baseline model. Experiments on the FlowEdit benchmark show that MaskFlow reduces LPIPS by 28.1% relative to the baseline while maintaining competitive semantic alignment.
The proposed MaskFlow, a training framework for precise localization, consistent background preservation, and seamless boundary transitions, incorporates the mask into the probability path and flow-matching objective, coordinating generation within the editable region with source preservation outside it.
Rui Xu, Yang Yong, Shun-Zi Yang et al.· 0 citations
DecFlowEdit is proposed, which decouples the optimal guidance scales for localization and for editing in flow-based generative models and first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CF...
Zhe-Yuan Zhan, Can Wang, Jia-Wei Chen et al.· 0 citations
IAB edited achieves state-of-the-art instruction adherence performance on RealEdit and EMU Edit benchmarks based on embedding-based metrics and shows that gradient-aligned VLM distillation holds up under real-world-like surveillance and occlusion conditions.
Chiranjeev Chiranjeev, Muskan Dosi, M. Vatsa et al.· European Conference on Compu...· 0 citations
Constrained Edit Fields (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.
Jing-Xuan Kang, Yin-Song Wang, Che Liu et al.· 1 citation
An instruction-guided image editing framework that integrates a Precision-Aware Localization Module and a Bidirectional Feature Enhancement Adapter that facilitates accurate and instruction-aware region localization without requiring any user-provided masks is proposed.
Yaya Lv, Li Liu, Daoguang Han et al.· Multimedia Systems· 0 citations
This work implements overpainting by adapting a pretrained image editing diffusion model using a combination of joint attention and low-rank adaption across input images with attention-dropout to balance the information flow between noise, source and mask images.
Sam Sartor, Iliyan Georgiev, Michael Fischer et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
