Through Van Gogh's Eyes: Global Style Transfer with Diffusion Mod

2026-08-11

AI Summary

This work addresses the limitations of existing artistic style transfer methods, which are often constrained by reliance on a single reference image or biased text prompts, hindering accurate modeling of an artist’s holistic style distribution. To overcome this, the paper introduces Global Style Transfer (GST), a novel Many-to-One paradigm that aggregates multiple artworks in the intermediate feature space of a diffusion model to learn a shared, artist-level style representation. Leveraging a training-free Global Style Guidance (GSG) mechanism alongside Content Alignment Guidance (CAG), the approach enables text-free style transfer that preserves semantic structure while allowing controllable deformations. Experiments on the WikiArt dataset demonstrate that the proposed method significantly outperforms current state-of-the-art techniques, achieving superior performance across three key metrics: style fidelity, content preservation, and output diversity.

Abstract

Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, making them effective for artwork-level stylization but limited in representing the broader stylistic distribution of an artist. Text-to-image diffusion models conditioned on artist names, such as '~ in Van Gogh style', offer greater flexibility, but they often suffer from text-induced bias and reproduce patterns from only a few iconic works. To address these limitations, we introduce Global Style Transfer (GST), an artistic image synthesis paradigm, in a Many-to-One manner, that aggregates multiple artworks from a target artist and transfers their shared global style to a single content image. For GST, we propose Global Style Guidance (GSG), which learns a residual global style offset in the intermediate feature space, or h-space, of a diffusion model under a fixed prompt. By learning artist-level style semantics purely from visual statistics, GSG mitigates text-dependent artistic bias. We further propose Content Alignment Guidance (CAG), a training-free perceptual guidance mechanism that preserves the semantic structure of the content image while allowing artist-specific geometric deformation. Experiments on WikiArt demonstrate that GST achieves superior stylistic fidelity, content preservation, and output diversity compared to existing style transfer and diffusion-based artistic synthesis methods.

Problem

• global style transfer
• artistic image synthesis
• diffusion models
• style bias
• artist-level stylization

Innovation

• Global Style Transfer
• Diffusion Models
• Style Guidance
• Content Preservation
• Artistic Synthesis