Skip to content
Open access

StyleSmith: A Signature Style Transfer Framework With Parametric and Temporal Attention

2026 · IEEE Access · Vol 14, pp. 148303-148336 · 0 citations · 49 references

TL;DR

StyleSmith is proposed, a diffusion framework for high-fidelity signature style transfer that supports local style transfer, texture transfer, and style-guided text-to-image generation, demonstrating strong academic innovation and industrial value.

Abstract

Artistic style transfer, which renders content images in the visual style of a reference artwork while preserving semantic structure, is a fundamental problem in computer vision and AIGC, with broad applications in digital art, commercial design, and creative media. Despite progress driven by diffusion-based approaches, signature style transfer, defined as the high-fidelity transfer of highly recognizable artistic traits such as exclusive geometric structures, personalized color schemes, brushstroke textures, and compositional logic, remains underexplored. Existing methods fall into two paradigms with critical limitations: training-free methods (e.g., StyleID, InstantStyle) enable efficient single-pass transfer but capture only shallow color and global texture features, failing to model fine-grained signature traits; tuning-based methods (e.g., InST) achieve stronger customization via text inversion but suffer from severe overfitting in one-shot fine-tuning, high computational cost, and content degradation. Four bottlenecks remain unresolved: insufficient fine-grained style capture, limited modeling from single reference images, an inherent style-content trade-off, and one-shot overfitting. To address these gaps, we propose StyleSmith, a diffusion framework for high-fidelity signature style transfer. First, a parametric style modulation network (PSM-Net) driven style-aware fine-tuning mechanism performs targeted optimization solely on the UNet decoder attention weights, identified as the core module for style learning, enabling accurate fine-grained style encoding from a single reference image, reducing tuned parameters by over 60%, and mitigating one-shot overfitting. Second, a temporal content preservation approach via attention anchoring (TCP-AA) injects content structural priors in early denoising stages and relaxes constraints in later stages, achieving a dynamic style-content balance analogous to an exploration-exploitation mechanism. Extensive experiments on WikiArt and ArtBench against 8 state-of-the-art methods show StyleSmith achieves the lowest style loss (0.7641, statistically significant, paired t-test $p \leq 0.033$ ) and FID (12.37), ranks second in content fidelity (LPIPS = 0.5191), and reduces fine-tuning time by nearly 50% versus comparable tuning-based methods. A user study with 25 evaluators further confirms StyleSmith’s perceptual superiority in style fidelity, content preservation, and overall quality. The framework also supports local style transfer, texture transfer, and style-guided text-to-image generation, demonstrating strong academic innovation and industrial value.

Read PDF

Similar papers

Conference Oct 2026

Diffusion-based image style transfer via parameter-free saliency recalibration

Image style transfer focuses on rendering a content image with the visual appearance of a reference artwork while keeping its main semantic layout unchanged. StyleID enables image-guided stylization without additional training by recording attention features during DDIM inversion, yet its results may still suffer from...

Hai-Tao Xin, Shi-Lin Bo · 0 citations
Open access Sep 2026

ArtNAS-Style: Style-Prior-Guided Differentiable Architecture Search for Artwork Recognition

Recognizing visual artworks is difficult because images of art combine large within-class diversity, ambiguous boundaries, and non-photographic textures with intertwined cues related to the artist, genre, style, and historical period. Standard convolutional or transformer models are commonly inherited from natural-imag...

Chun-Hu Shi, Shu Gong, Ji-Ye He · 0 citations
Conference 2026

FlowLess: Controlling Abstract Image Generation

A novel self-supervised framework that enables granular control over image generation through a visual abstraction set that provides a richer, more flexible paradigm for creative design compared to state-of-the-art baselines across diverse styles and compositions is introduced.

Amir Hertz, Noah Snavely · 0 citations
Open access Oct 2026

Lightweight Artistic Style Classification via Texture Correlation and Adaptive Local–Global Fusion

Artistic style classification remains challenging because visually similar styles often exhibit subtle differences in brushstrokes, textures, colors, and global composition. To address this problem, this paper proposes a lightweight artistic style classification framework based on a MobileNet–Transformer Hybrid (MTH)....

Jin-Jiang Zhao, Peng Ren, Rui Guo et al. · 0 citations
Preprint Sep 2026

CLeaR: A Unified Framework for Resolving the Leakage-Degradation Dilemma in Style Transfer

CLeaR, a training-free framework for content-leakage-resistant style transfer, is proposed and experiments demonstrate that CLeaR improves style alignment, reduces content leakage, and achieves better LLM-as-Judge evaluation compared with existing methods.

Teng Zhou, Yunhao Chen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.