U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation
This work addresses the challenge of disentangling visual attributes in image personalization for users of text-to-image models, representing an incremental improvement over existing methods.
The paper tackles the problem of fine-grained visual appearance personalization in text-to-image models, where existing methods overfit to entire subjects and cannot disentangle specific visual attributes. The proposed method uses a decoupled self-augmentation strategy to learn user-specified attributes, improving controllability and flexibility in synthesizing renditions in new contexts.
Concept personalization methods enable large text-to-image models to learn specific subjects (e.g., objects/poses/3D models) and synthesize renditions in new contexts. Given that the image references are highly biased towards visual attributes, state-of-the-art personalization models tend to overfit the whole subject and cannot disentangle visual characteristics in pixel space. In this study, we proposed a more challenging setting, namely fine-grained visual appearance personalization. Different from existing methods, we allow users to provide a sentence describing the desired attributes. A novel decoupled self-augmentation strategy is proposed to generate target-related and non-target samples to learn user-specified visual attributes. These augmented data allow for refining the model's understanding of the target attribute while mitigating the impact of unrelated attributes. At the inference stage, adjustments are conducted on semantic space through the learned target and non-target embeddings to further enhance the disentanglement of target attributes. Extensive experiments on various kinds of visual attributes with SOTA personalization methods show the ability of the proposed method to mimic target visual appearance in novel contexts, thus improving the controllability and flexibility of personalization.