Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning

Citations Over TimeTop 1% of 2022 papers

Abstract

In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a key component in image stylization tasks, is essential to achieve satisfactory results. Existing deep neural network based approaches achieve reasonable results with the guidance from second-order statistics such as Gram matrix of content features. However, they do not leverage sufficient style information, which results in artifacts such as local distortions and style inconsistency. To address these issues, we propose to learn style representation directly from image features instead of their second-order statistics, by analyzing the similarities and differences between multiple styles and considering the style distribution. Specifically, we present Contrastive Arbitrary Style Transfer (CAST), which is a new style representation learning and style transfer method via contrastive learning. Our framework consists of three key components, i.e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer. We conduct qualitative and quantitative evaluations comprehensively to demonstrate that our approach achieves significantly better results compared to those obtained via state-of-the-art methods. Code and models are available at https://github.com/zyxElsa/CAST_pytorch.

Related Papers

• → Performance of True Transfer Learning using CNN DenseNet121 for COVID-19 Detection from Chest X-Ray Images(2021)22 cited
• Elizabethan & Jacobean Style(1993)
• → Theoretical and methodological approaches to the study of “severe style” and its manifestation in the works of Siberian artists on the example of a landscape(2022)1 cited
• The Quality of The Style of Commentaries on Classics and The Differences between The Official Style and The Unofficial Style(2006)
• Nanjing-style Illustrations in A Journey to the West and the Spread of the Book:Differences and Similarities of the Illustrations among Nanjing-style,Huizhou-style and Jianyang-style(2009)