Preserving Color in Neural Artistic Style Transfer

By Leon A. Gatys, Matthias Bethge, Aaron Hertzmann, Eli Shechtman. 2016

147 citations recorded by the source corpus.

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.

Subfields: Cognitive Neuroscience, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (2017, neutral): “Neural Style Transfer [11, 21, 48, 10] is another way to perform image-to-image translation, which synthesizes a novel image by combining the content of one image with the style of another image (typically a painting) by matching the Gram matrix statistics of pre-trained deep features.”
A Learned Representation For Artistic Style (2016, methodology): “Subsequent work has brought some performance improvements to style transfer networks, e.g. with respect to color preservation (Gatys et al., 2016a) or style transfer quality (Ulyanov et al., 2016b), but to our knowledge the problem of the single-purpose nature of style transfer networks remains…”
Style Transfer in Text: Exploration and Evaluation (2017, background): “…is an important problem in many subﬁelds of artiﬁcial intelligence (AI), such as natural language processing (NLP) and computer vision (Gatys, Ecker, and Bethge 2016; Gatys et al. 2016; Zhu et al. 2017; Li et al. 2017), as it reﬂects the ability of intelligence systems to generate novel contents.”
Visual attribute transfer through deep image analogy (2017, methodology): “Neural style [Gatys et al. 2016b] and perceptual loss methods [Johnson et al. 2016] rely on global statistics matching, and as a result, do not guarantee local structure-to-structure transfer.”
Photorealistic Facial Texture Inference Using Deep Neural Networks (2016, methodology): “[16, 15] recently proposed a style-transfer technique using deep neural networks that has the ability to seamlessly blend the content from one highresolution image with the style of another while preserving consistent structures of low and high-level visual features.”
Neural Style Transfer: A Review (2017, background): “[13, 17] themselves propose several slight modiﬁcations to improve their previous algorithm.”
MIXGAN: Learning Concepts from Different Domains for Mixture Generation (2018, methodology): “On the other hand, although the style transfer [Gatys et al., 2016; Johnson et al., 2016; Ulyanov et al., 2016] and image-to-image translation [Hertzmann et al.”
Multi-style Generative Network for Real-time Transfer (2017, methodology): “In addition, MSG-Net as a general multi-style strategy is compatible to most existing techniques and progress in style transfer, such as content style trade-off and interpolation [9], spatial control, color preserving and brush-size control [14, 16].”