StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition
By Xiaolei Wu, Zhihao Hu, Lu Sheng, Dong Xu. 2021
135 citations recorded by the source corpus.
In this work, we propose a new feed-forward arbitrary style transfer method, referred to as StyleFormer, which can simultaneously fulfill fine-grained style diversity and semantic content coherency. Specifically, our transformer-inspired feature-level stylization method consists of three modules: (a) the style bank generation module for sparse but compact parametric style pattern extraction, (b) the transformer-driven style composition module for content-guided global style composition, and (c) the parametric content modulation module for flexible but faithful stylization. The output stylized images are impressively coherent with the content structure, sensitive to the detailed style variations, but still holistically adhere to the style distributions from the style images. Qualitative and quantitative comparisons as well as comprehensive user studies demonstrate that our StyleFormer outperforms the existing SOTA methods in generating visually plausible stylization results with real-time efficiency.
Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Graphics and Computer-Aided Design
- Fan Tang
- Mubarak Shah
- Changsheng Xu
- Munawar Hayat
- Chongyang Ma
- Salman Hameed Khan
- Fahad Shahbaz Khan
- Syed Waqas Zamir
In Computer Vision and Pattern Recognition
- Fahad Shahbaz Khan
- Salman Hameed Khan
- Ming-Hsuan Yang
- Munawar Hayat
- Luc Van Gool
- Syed Waqas Zamir
- Changsheng Xu
- Muzammal Naseer
Citations in the corpus
- Transformers in Vision: A Survey (2021, methodology): “A related work StyleFromer [220] uses feature level information to transfer styles with transformer-based encoding and decoding mechanisms.”
- StyTr2: Image Style Transfer with Transformers (2021, methodology): “StyleFormer [56] adopts the transformer mechanism into the traditional CNN-based encoder-decoder pipeline.”
- Inversion-based Style Transfer with Diffusion Models (2022, methodology): “[55] perform content-guided global style composition by a transformer-driven style composition module”