Style Mixer: Semantic-aware Multi-Style Transfer Network

TL;DR

This paper introduces a novel multi-style transfer framework that automatically combines multiple styles into one image based on semantic regions, improving visual quality and diversity over existing methods.

Contribution

It presents the first multi-style transfer network that uses semantic-aware modules and a region-based style fusion approach for improved stylization.

Findings

Outperforms existing single-style and multi-style transfer methods.

Achieves better semantic correspondence and style detail preservation.

Demonstrates versatile and visually pleasing multi-style transfer results.

Abstract

Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single-style Transfer (SST), but little attention has been paid to Multi-style Transfer (MST) which refers to simultaneously transferring multiple styles to the same image. Compared to SST, MST has the potential to create more diverse and visually pleasing stylization results. In this paper, we propose the first MST framework to automatically incorporate multiple styles into one result based on regional semantics. We first improve the existing SST backbone network by introducing a novel multi-level feature fusion module and a patch attention module to achieve better semantic correspondences and preserve richer style details. For MST, we designed a conceptually simple yet effective region-based style fusion module to insert into the backbone. It assigns corresponding styles to content regions based on semantic matching, and then seamlessly combines multiple styles together. Comprehensive evaluations demonstrate that our framework outperforms existing works of SST and MST.