TextureDiffusion：面向多样纹理迁移的目标提示解耦编辑
TextureDiffusion: Target Prompt Disentangled Editing for Various Texture Transfer
AI总结：
针对现有文本引导图像编辑方法难以迁移复杂纹理的问题，提出无需调优的TextureDiffusion方法，通过提示解耦、结构特征保留与编辑定位技术，实现多样纹理的和谐迁移及结构、背景的有效保留。
摘要：
近年来，文本引导的图像编辑已取得显著成效。然而，现有方法在改变物体纹理时，仅能应用木材、黄金等简单纹理，云朵、火焰等复杂纹理则构成挑战。这一局限源于目标提示需同时包含输入图像内容与<纹理>，限制了纹理的表征能力。本文提出TextureDiffusion，一种适用于多样纹理迁移的无需调优的图像编辑方法。首先，将目标提示直接设为“<纹理>”，使纹理与输入图像内容解耦，以增强纹理表征；随后，利用自注意力中的查询特征与残差块中的特征保留输入图像的结构；最后，为保留背景，引入一种编辑定位技术，融合自注意力结果与中间潜变量。综合实验表明，TextureDiffusion能够和谐迁移多样纹理，同时具备出色的结构与背景保留效果。代码已公开于https://github.com/THU-CVML/TextureDiffusion。
英文摘要：
Recently, text-guided image editing has achieved significant success. However, existing methods can only apply simple textures like wood or gold when changing the texture of an object. Complex textures such as cloud or fire pose a challenge. This limitation stems from that the target prompt needs to contain both the input image content and <texture>, restricting the texture representation. In this paper, we propose TextureDiffusion, a tuning-free image editing method applied to various texture transfer. Initially, the target prompt is directly set to "<texture>", making the texture disentangled from the input image content to enhance texture representation. Subsequently, query features in self-attention and features in residual blocks are utilized to preserve the structure of the input image. Finally, to maintain the background, we introduce an edit localization technique which blends the self-attention results and the intermediate latents. Comprehensive experiments demonstrate that TextureDiffusion can harmoniously transfer various textures with excellent structure and background preservation. Code is publicly available at https://github.com/THU-CVML/TextureDiffusion
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。
