U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation

TL;DR

U-VAP introduces a novel approach for fine-grained visual appearance personalization in text-to-image models, using decoupled self-augmentation to better disentangle and control target attributes based on user descriptions.

Contribution

The paper proposes a decoupled self-augmentation strategy for improved disentanglement of visual attributes in personalization, enabling more precise control over target appearance.

Findings

Outperforms state-of-the-art methods in visual attribute control

Enhances model's ability to generate target-specific appearances in new contexts

Improves disentanglement of target and non-target attributes during personalization

Abstract

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.