通过对比参考图自动分离用户概念，提升个性化图像生成精度。
ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
- 用跨图对比提取共享特征，无需人工标注。
- 目标令牌与残差令牌联合优化，实现概念解耦。
- 适合需要高保真个性化图像生成的研究者使用。
个性化文本到图像生成已成为从少量参考图像创建用户特定概念的关键应用。核心挑战是概念解耦：将目标概念与无关的残余信息分离。若缺乏解耦，捕捉高保真特征时常引入与用户提示冲突的非预期属性，破坏概念保真度与文本对齐之间的平衡。现有方法依赖人工引导，常无法表征复杂视觉细节且难以扩展。本文提出ConceptPrism，一种通过跨图像比较提取共享特征、无需外部信息的框架。通过重建损失与排除损失联合优化目标令牌和图像级残差令牌。抑制残差令牌中的共享信息后，排除损失制造信息空缺，迫使目标令牌捕获共性概念。大量实验表明，ConceptPrism实现了精确的概念解耦，并在多样化复杂视觉概念上显著提升整体性能。代码已开源：https://github.com/Minseo-Kimm/ConceptPrism。
原文摘要 · Abstract (English)
Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant residual information. Lacking such disentanglement, capturing high-fidelity features often incorporates undesired attributes that conflict with user prompts, compromising the trade-off between concept fidelity and text alignment. While existing methods rely on manual guidance, they often fail to represent intricate visual details and lack scalability. We introduce ConceptPrism, a framework that extracts shared features exclusively through cross-image comparison without external information. We jointly optimize a target token and image-wise residual tokens via reconstruction and exclusion losses. By suppressing shared information in residual tokens, the exclusion loss creates an information vacuum that forces the target token to capture the common concept. Extensive evaluations demonstrate that ConceptPrism achieves accurate concept disentanglement and significantly improves overall performance across diverse and complex visual concepts. The code is available at https://github.com/Minseo-Kimm/ConceptPrism.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。