Style Transfer with Target Feature Palette and Attention Coloring

TL;DR

This paper introduces a novel style transfer method using target feature palettes and attention coloring modules, which accurately transfer key features and preserve image details, outperforming existing approaches.

Contribution

The paper proposes a new deep learning-based style transfer technique with innovative feature palette composition and attention coloring modules, along with comprehensive analysis and ablation studies.

Findings

State-of-the-art performance in style transfer quality

Enhanced preservation of content image structures and details

Effective transfer of colors and patterns based on attention maps

Abstract

Style transfer has attracted a lot of attentions, as it can change a given image into one with splendid artistic styles while preserving the image structure. However, conventional approaches easily lose image details and tend to produce unpleasant artifacts during style transfer. In this paper, to solve these problems, a novel artistic stylization method with target feature palettes is proposed, which can transfer key features accurately. Specifically, our method contains two modules, namely feature palette composition (FPC) and attention coloring (AC) modules. The FPC module captures representative features based on K-means clustering and produces a feature target palette. The following AC module calculates attention maps between content and style images, and transfers colors and patterns based on the attention map and the target palette. These modules enable the proposed stylization to focus on key features and generate plausibly transferred images. Thus, the contributions of the proposed method are to propose a novel deep learning-based style transfer method and present target feature palette and attention coloring modules, and provide in-depth analysis and insight on the proposed method via exhaustive ablation study. Qualitative and quantitative results show that our stylized images exhibit state-of-the-art performance, with strength in preserving core structures and details of the content image.