DynASyn：支持动态动作合成的多主体个性化方法
DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesis
AI总结：
针对现有图像个性化方法难以修改主体动态行为、单参考图下易过拟合的问题，提出DynASyn多主体个性化方法，通过概念先验对齐与增强策略平衡身份保留和动作多样性，效果优于基线方法。
摘要：
文本到图像扩散模型的最新进展推动了个性化研究，即对参考图像中的主体进行定制化图像合成。现有个性化方法虽能改变主体位置或同时对多个主体进行个性化，但往往难以修改主体的行为或它们之间的动态交互。这一难点源于对参考图像的过拟合，若仅有单张参考图像，过拟合问题会更严重。我们提出DynASyn，一种有效的单参考图像多主体个性化方法，以解决上述挑战。DynASyn通过将基于概念的先验与主体外观和动作对齐，在个性化过程中保留主体身份。这一目标通过基于概念的先验对主体token与图像之间的注意力图进行正则化实现。此外，我们提出基于概念的提示-图像增强方法，以更好地平衡身份保留与动作多样性。我们采用由增强提示引导的基于SDE的编辑方法，在增强图像中保持身份一致性的同时，生成多样的外观和动作。实验表明，DynASyn能够合成具有新颖场景、主体与周围环境存在动态交互的高度真实图像，且在定量和定性指标上均优于基线方法。
英文摘要：
Recent advances in text-to-image diffusion models spurred research on personalization, i.e., a customized image synthesis, of subjects within reference images. Although existing personalization methods are able to alter the subjects' positions or to personalize multiple subjects simultaneously, they often struggle to modify the behaviors of subjects or their dynamic interactions. The difficulty is attributable to overfitting to reference images, which worsens if only a single reference image is available. We propose DynASyn, an effective multi-subject personalization from a single reference image addressing these challenges. DynASyn preserves the subject identity in the personalization process by aligning concept-based priors with subject appearances and actions. This is achieved by regularizing the attention maps between the subject token and images through concept-based priors. In addition, we propose concept-based prompt-and-image augmentation for an enhanced trade-off between identity preservation and action diversity. We adopt an SDE-based editing guided by augmented prompts to generate diverse appearances and actions while maintaining identity consistency in the augmented images. Experiments show that DynASyn is capable of synthesizing highly realistic images of subjects with novel contexts and dynamic interactions with the surroundings, and outperforms baseline methods in both quantitative and qualitative aspects.
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。
