FAGStyle: Feature Augmentation on Geodesic Surface for Zero-shot Text-guided Diffusion Image Style Transfer
This work addresses style consistency and content preservation issues in text-guided image style transfer, offering a flexible alternative to image-guided methods, though it appears incremental as it builds on existing diffusion techniques.
The paper tackled the problem of text-guided diffusion image style transfer, which often struggles with style consistency and content preservation, by introducing FAGStyle, a method that achieved superior performance in maintaining semantic content and style accuracy across diverse datasets.
The goal of image style transfer is to render an image guided by a style reference while maintaining the original content. Existing image-guided methods rely on specific style reference images, restricting their wider application and potentially compromising result quality. As a flexible alternative, text-guided methods allow users to describe the desired style using text prompts. Despite their versatility, these methods often struggle with maintaining style consistency, reflecting the described style accurately, and preserving the content of the target image. To address these challenges, we introduce FAGStyle, a zero-shot text-guided diffusion image style transfer method. Our approach enhances inter-patch information interaction by incorporating the Sliding Window Crop technique and Feature Augmentation on Geodesic Surface into our style control loss. Furthermore, we integrate a Pre-Shape self-correlation consistency loss to ensure content consistency. FAGStyle demonstrates superior performance over existing methods, consistently achieving stylization that retains the semantic content of the source image. Experimental results confirms the efficacy of FAGStyle across a diverse range of source contents and styles, both imagined and common.