LoMOE：基于多扩散的局部多对象编辑
LoMOE: Localized Multi-Object Editing via Multi-Diffusion
AI总结：
提出 LoMOE 零样本多扩散框架，结合前景掩码、文本提示及潜在空间约束，实现复杂场景中一次性局部多对象编辑，并发布 LoMOE-Bench 数据集。
摘要：
扩散模型领域的最新进展已展现出生成高质量、以提示为条件的图像编辑的卓越能力。然而，以往方法主要依赖文本提示进行图像编辑，当需要在包含单个或多个对象的场景中对特定对象或细粒度区域进行精确编辑时，这类方法往往效果不佳。为克服这一挑战，我们提出了一种通过多扩散过程实现零样本局部多对象编辑的新颖框架。该框架使用户能够对图像中的对象执行多种操作，例如在复杂场景中一次性添加、替换或编辑许多对象。我们的方法利用前景掩码和相应的简单文本提示，对目标区域施加局部影响，从而实现高保真图像编辑。在潜在空间中结合交叉注意力损失和背景保持损失，可确保被编辑对象的特征得到保留，同时实现高质量、无缝的背景重建，并且与现有方法相比伪影更少。我们还整理并发布了一个专用于多对象编辑的数据集，命名为 LoMOE-Bench。与现有最先进方法的对比实验表明，我们的方法在图像编辑质量和推理速度两方面均具有更优的有效性。
英文摘要：
Recent developments in the field of diffusion models have demonstrated an exceptional capacity to generate high-quality prompt-conditioned image edits. Nevertheless, previous approaches have primarily relied on textual prompts for image editing, which tend to be less effective when making precise edits to specific objects or fine-grained regions within a scene containing single/multiple objects. We introduce a novel framework for zero-shot localized multi-object editing through a multi-diffusion process to overcome this challenge. This framework empowers users to perform various operations on objects within an image, such as adding, replacing, or editing $\textbf{many}$ objects in a complex scene $\textbf{in one pass}$. Our approach leverages foreground masks and corresponding simple text prompts that exert localized influences on the target regions resulting in high-fidelity image editing. A combination of cross-attention and background preservation losses within the latent space ensures that the characteristics of the object being edited are preserved while simultaneously achieving a high-quality, seamless reconstruction of the background with fewer artifacts compared to the current methods. We also curate and release a dataset dedicated to multi-object editing, named $\texttt{LoMOE}$-Bench. Our experiments against existing state-of-the-art methods demonstrate the improved effectiveness of our approach in terms of both image editing quality and inference speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
