Arbitrary Style Transfer Based on Content Integrity and Style Consistency Enhancement

Abstract

The existing arbitrary style transfer methods mainly suffer two challenges. One is content integrity, as most methods focus too much on style, resulting in incomplete content information and missing details. The other is style consistency, which requires more exploration of style information to alleviate pattern and texture inconsistencies. Thus, a framework of Content Integrity and Style Consistency preserving arbitrary style transfer (CISC-ST) is proposed, which consists of a Dual Style Attention (DSA) mechanism and Frequency Domain Enhancement (FDE) architecture. The DSA aims to explore more style information and generate finer-grained style details. The FDE aims to enhance the overall content information to improve content preservation. Qualitative and quantitative experiments show that our method can produce stylized results that are more detailed in content and visually harmonious. The source code of our CISC-ST is available at https://github.com/SWU-CS-MediaLab/CISC-ST.