Artistic style transfer with internal-external learning and contrastive learning

H Chen, Z Wang, H Zhang, Z Zuo, A Li… - Advances in …, 2021 - proceedings.neurips.cc
Although existing artistic style transfer methods have achieved significant improvement with
deep neural networks, they still suffer from artifacts such as disharmonious colors and …

Stylediffusion: Controllable disentangled style transfer via diffusion models

Z Wang, L Zhao, W Xing - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Content and style (CS) disentanglement is a fundamental problem and critical challenge of
style transfer. Existing approaches based on explicit definitions (eg, Gram matrix) or implicit …

Learning graph neural networks for image style transfer

Y Jing, Y Mao, Y Yang, Y Zhan, M Song… - … on Computer Vision, 2022 - Springer
State-of-the-art parametric and non-parametric style transfer approaches are prone to either
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …

Style-hallucinated dual consistency learning for domain generalized semantic segmentation

Y Zhao, Z Zhong, N Zhao, N Sebe, GH Lee - European conference on …, 2022 - Springer
In this paper, we study the task of synthetic-to-real domain generalized semantic
segmentation, which aims to learn a model that is robust to unseen real-world scenes using …

Quantart: Quantizing image style transfer towards high visual fidelity

S Huang, J An, D Wei, J Luo… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to
push the generated image toward high similarities in both content and style. However, this …

AesUST: towards aesthetic-enhanced universal style transfer

Z Wang, Z Zhang, L Zhao, Z Zuo, A Li, W Xing… - Proceedings of the 30th …, 2022 - dl.acm.org
Recent studies have shown remarkable success in universal style transfer which transfers
arbitrary visual styles to content images. However, existing approaches suffer from the …

Draw your art dream: Diverse digital art synthesis with multimodal guided diffusion

N Huang, F Tang, W Dong, C Xu - Proceedings of the 30th ACM …, 2022 - dl.acm.org
Digital art synthesis is receiving increasing attention in the multimedia community because
of engaging the public with art effectively. Current digital art synthesis methods usually use …

MicroAST: towards super-fast ultra-resolution arbitrary style transfer

Z Wang, L Zhao, Z Zuo, A Li, H Chen, W Xing… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite
the recent rapid progress, existing AST methods are either incapable or too slow to run at …

Style-hallucinated dual consistency learning: A unified framework for visual domain generalization

Y Zhao, Z Zhong, N Zhao, N Sebe, GH Lee - International Journal of …, 2024 - Springer
Abstract Domain shift widely exists in the visual world, while modern deep neural networks
commonly suffer from severe performance degradation under domain shift due to poor …

Artfid: Quantitative evaluation of neural style transfer

M Wright, B Ommer - DAGM German Conference on Pattern Recognition, 2022 - Springer
The field of neural style transfer has experienced a surge of research exploring different
avenues ranging from optimization-based approaches and feed-forward models to meta …