Arbitrary Style Transfer with Deep Feature Reshuffle

Abstract

This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theoretically prove that our new style loss based on reshuffle connects both global and local style losses respectively used by most parametric and non-parametric neural style transfer methods. This simple idea can effectively address the challenging issues in existing style transfer methods. On one hand, it can avoid distortions in local style patterns, and allow semantic-level transfer, compared with neural parametric methods. On the other hand, it can preserve globally similar appearance to the style image, and avoid wash-out artifacts, compared with neural non-parametric methods. Based on the proposed loss, we also present a progressive feature-domain optimization approach. The experiments show that our method is widely applicable to various styles, and produces better quality than existing methods.

Cited by in corpus (6)

• Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Anisotropic Stroke Control for Multiple Artists Style Transfer
• Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
• Unpaired Image Translation via Adaptive Convolution-based Normalization
• Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation