Search papers, labs, and topics across Lattice.
This paper introduces Global Style Transfer (GST), a novel artistic image synthesis approach that captures the broader stylistic distribution of an artist by aggregating multiple artworks in a Many-to-One manner. The method employs Global Style Guidance (GSG) to learn a residual global style offset in the intermediate feature space of a diffusion model, effectively reducing text-induced bias while preserving artistic integrity. Experimental results on WikiArt show that GST significantly outperforms traditional style transfer and diffusion methods in terms of stylistic fidelity, content preservation, and output diversity.
By aggregating multiple artworks, Global Style Transfer captures the essence of an artist's style without the biases of text prompts, achieving unprecedented fidelity and diversity in artistic synthesis.
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.
