DesignEdit：用于统一且精准图像编辑的多层潜在分解与融合
DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing
AI总结：
本文提出DesignEdit框架，通过将空间感知图像编辑转化为多层潜在分解与多层潜在融合两个子任务，利用键掩码自注意力与指令引导融合等机制，在六种以上编辑任务中实现了统一且精准的图像编辑。
摘要：
近期，如何实现精准的图像编辑引起了越来越多的关注，特别是鉴于文本到图像生成模型取得的显著成功。为了将各种空间感知的图像编辑能力统一到一个框架中，我们采用了设计领域的图层概念，以通过多种操作灵活地操作对象。关键见解是将空间感知的图像编辑任务转化为两个子任务的组合：多层潜在分解和多层潜在融合。首先，我们将源图像的潜在表示分割为多个图层，其中包括几个对象层和一个需要可靠修复的不完整背景层。为了避免额外微调，我们进一步探索了自注意力机制内部的修复能力。我们引入了一种键掩码自注意力方案，该方案能将周围的上下文信息传播到掩码区域，同时减轻其对掩码外部区域的影响。其次，我们提出了一种指令引导的潜在融合方法，将多层潜在表示粘贴到画布潜在空间上。我们还引入了潜在空间中的伪影抑制方案以增强修复质量。由于此类多层表示固有的模块化优势，我们能够实现精准的图像编辑，并且我们证明我们的方法持续超越了最新的空间编辑方法，包括 Self-Guidance 和 DiffEditor。最后，我们展示了我们的方法是一个统一框架，支持在六种以上不同的编辑任务中进行各种精准的图像编辑任务。
英文摘要：
Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we adopt the concept of layers from the design domain to manipulate objects flexibly with various operations. The key insight is to transform the spatial-aware image editing task into a combination of two sub-tasks: multi-layered latent decomposition and multi-layered latent fusion. First, we segment the latent representations of the source images into multiple layers, which include several object layers and one incomplete background layer that necessitates reliable inpainting. To avoid extra tuning, we further explore the inner inpainting ability within the self-attention mechanism. We introduce a key-masking self-attention scheme that can propagate the surrounding context information into the masked region while mitigating its impact on the regions outside the mask. Second, we propose an instruction-guided latent fusion that pastes the multi-layered latent representations onto a canvas latent. We also introduce an artifact suppression scheme in the latent space to enhance the inpainting quality. Due to the inherent modular advantages of such multi-layered representations, we can achieve accurate image editing, and we demonstrate that our approach consistently surpasses the latest spatial editing methods, including Self-Guidance and DiffEditor. Last, we show that our approach is a unified framework that supports various accurate image editing tasks on more than six different editing tasks.
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。
