Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses

Abstract

Recently, methods have been proposed that perform texture synthesis and style transfer by using convolutional neural networks (e.g. Gatys et al. [2015,2016]). These methods are exciting because they can in some cases create results with state-of-the-art quality. However, in this paper, we show these methods also have limitations in texture quality, stability, requisite parameter tuning, and lack of user controls. This paper presents a multiscale synthesis pipeline based on convolutional neural networks that ameliorates these issues. We first give a mathematical explanation of the source of instabilities in many previous approaches. We then improve these instabilities by using histogram losses to synthesize textures that better statistically match the exemplar. We also show how to integrate localized style losses in our multiscale framework. These losses can improve the quality of large features, improve the separation of content and style, and offer artistic controls such as paint by numbers. We demonstrate that our approach offers improved quality, convergence in fewer iterations, and more stability over the optimization.

References in corpus (1)

• Fast Patch-based Style Transfer of Arbitrary Style

Cited by in corpus (24)

• On Demand Solid Texture Synthesis Using Deep 3D Networks
• Style Mixer: Semantic-aware Multi-Style Transfer Network
• Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Meta Networks for Neural Style Transfer
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
• Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
• NITES: A Non-Parametric Interpretable Texture Synthesis Method
• Recovering Faces from Portraits with Auxiliary Facial Attributes
• EDIT: Exemplar-Domain Aware Image-to-Image Translation
• TGHop: An Explainable, Efficient and Lightweight Method for Texture Generation
• FaceController: Controllable Attribute Editing for Face in the Wild
• Fast Universal Style Transfer for Artistic and Photorealistic Rendering
• Style-Aware Normalized Loss for Improving Arbitrary Style Transfer
• Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport
• Defective samples simulation through Neural Style Transfer for automatic surface defect segment
• Style is a Distribution of Features
• GANILLA: Generative Adversarial Networks for Image to Illustration Translation
• Global Image Sentiment Transfer
• Trace-Norm Adversarial Examples
• Neural Style Difference Transfer and Its Application to Font Generation
• Non-Parametric Neural Style Transfer
• CAMS: Color-Aware Multi-Style Transfer