PrimeComposer：通过注意力引导实现更快速的渐进式组合扩散模型用于图像合成
PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
AI总结：
本文提出PrimeComposer，一种免训练的快速扩散模型，通过相关性扩散器进行跨噪声水平的注意力引导，并引入区域约束交叉注意力，实现高质量且高效的前景聚焦图像合成。
摘要：
图像合成涉及将给定对象无缝集成到特定视觉环境中。当前的免训练方法依赖于组合多个采样器的注意力权重来引导生成器。然而，由于这些权重源自不同的上下文，它们的组合会导致连贯性混淆和外观信息丢失。这些问题因其过度关注背景生成而加剧，即使在此任务中背景生成并非必要。这不仅阻碍了它们的快速实现，也损害了前景生成质量。此外，这些方法在过渡区域引入了不必要的伪影。在本文中，我们将图像合成定义为基于主体的局部编辑任务，仅关注前景生成。在每一步中，编辑后的前景与带噪声的背景相结合以保持场景一致性。为解决剩余问题，我们提出了PrimeComposer，一种更快速的免训练扩散器，通过在不同噪声水平上精心设计的注意力引导来合成图像。这种引导主要通过我们的相关性扩散器（Correlation Diffuser）实现，利用其每一步的自注意力层。在这些层中，合成主体与参考对象和背景相互作用，捕捉复杂细节和连贯关系。这些先验信息被编码到注意力权重中，然后集成到生成器的自注意力层以引导合成过程。此外，我们引入了区域约束的交叉注意力（Region-constrained Cross-Attention），将特定主体相关令牌的影响限制在期望区域内，解决了先前方法中出现的伪影问题，从而进一步提高了过渡区域的连贯性。我们的方法展现出最快的推理效率，大量实验在定性和定量上均证明了我们的优越性。
英文摘要：
Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are derived from disparate contexts, their combination leads to coherence confusion and loss of appearance information. These issues worsen with their excessive focus on background generation, even when unnecessary in this task. This not only impedes their swift implementation but also compromises foreground generation quality. Moreover, these methods introduce unwanted artifacts in the transition area. In this paper, we formulate image composition as a subject-based local editing task, solely focusing on foreground generation. At each step, the edited foreground is combined with the noisy background to maintain scene consistency. To address the remaining issues, we propose PrimeComposer, a faster training-free diffuser that composites the images by well-designed attention steering across different noise levels. This steering is predominantly achieved by our Correlation Diffuser, utilizing its self-attention layers at each step. Within these layers, the synthesized subject interacts with both the referenced object and background, capturing intricate details and coherent relationships. This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process. Besides, we introduce a Region-constrained Cross-Attention to confine the impact of specific subject-related tokens to desired regions, addressing the unwanted artifacts shown in the prior method thereby further improving the coherence in the transition area. Our method exhibits the fastest inference efficiency and extensive experiments demonstrate our superiority both qualitatively and quantitatively.
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。
