Preserving Color in Neural Artistic Style Transfer

Abstract

This note presents an extension to the neural artistic style transfer algorithm (Gatys et al.). The original algorithm transforms an image to have the style of another given image. For example, a photograph can be transformed to have the style of a famous painting. Here we address a potential shortcoming of the original method: the algorithm transfers the colors of the original painting, which can alter the appearance of the scene in undesirable ways. We describe simple linear methods for transferring style while preserving colors.

Cited by in corpus (32)

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Style-Transfer via Texture-Synthesis
• Multi-style Generative Network for Real-time Transfer
• Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
• Visual Attribute Transfer through Deep Image Analogy
• ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks
• Style Transfer in Text: Exploration and Evaluation
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Diversified Texture Synthesis with Feed-forward Networks
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Applying Visual Domain Style Transfer and Texture Synthesis Techniques to Audio - Insights and Challenges
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• Photorealistic Facial Texture Inference Using Deep Neural Networks
• Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
• Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
• GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework
• Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
• MIXGAN: Learning Concepts from Different Domains for Mixture Generation
• Learning Selfie-Friendly Abstraction from Artistic Style Images
• Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport
• Using a Bi-directional LSTM Model with Attention Mechanism trained on MIDI Data for Generating Unique Music
• Cycle-consistent Generative Adversarial Networks for Neural Style Transfer using data from Chang'E-4
• Global Image Sentiment Transfer
• Multi-Pair Text Style Transfer on Unbalanced Data
• CAMS: Color-Aware Multi-Style Transfer
• Neural Style Difference Transfer and Its Application to Font Generation
• A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer
• Evolutionary Image Transition and Painting Using Random Walks
• Making a Case for Learning Motion Representations with Phase
• Learning to Transfer Visual Effects from Videos to Images