Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer (2018-12-10T00:00:00.000000Z)

TL;DR

Two approaches proposed: a two-stage model and an end-to-end model are proposed that are able to not only generate stylized images of quality comparable with the ones produced by typical style transfer methods, but also effectively eliminate the artifacts introduced in reconstructing original input from a stylized image.

Abstract

Style transfer has been widely applied to give real-world images a new artistic look. However, given a stylized image, the attempts to use typical style transfer methods for de-stylization or transferring it again into another style usually lead to artifacts or undesired results. We realize that these issues are originated from the content inconsistency between the original image and its stylized output. Therefore, in this paper we advance to keep the content information of the input image during the process of style transfer by the power of steganography, with two approaches proposed: a two-stage model and an end-to-end model. We conduct extensive experiments to successfully verify the capacity of our models, in which both of them are able to not only generate stylized images of quality comparable with the ones produced by typical style transfer methods, but also effectively eliminate the artifacts introduced in reconstructing original input from a stylized image as well as performing multiple times of style transfer in series.

Authors

Wei-Chen Chiu

4 papers

Hung-Yu Chen

1 papers

I-Sheng Fang

1 papers

TL;DR

Abstract

Authors

References34 items

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation

HiDDeN: Hiding Data With Deep Networks

The relativistic discriminator: a key element missing from standard GAN

Avatar-Net: Multi-scale Zero-Shot Style Transfer by Feature Decoration

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

Identity-Preserving Face Recovery from Portraits

Hiding Images in Plain Sight: Deep Steganography

Face Destylization

Automatic differentiation in PyTorch

Universal Style Transfer via Feature Transforms

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

Generating steganographic images via adversarial training

Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis

Image-to-Image Translation with Conditional Adversarial Networks

A Learned Representation For Artistic Style

Image Style Transfer Using Convolutional Neural Networks

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

Texture Synthesis Using Convolutional Neural Networks

Adam: A Method for Stochastic Optimization

Very Deep Convolutional Networks for Large-Scale Image Recognition

Microsoft COCO: Common Objects in Context

Data-driven hallucination of different times of day from a single outdoor photo

Information Hiding Using Least Significant Bit Steganography and Cryptography

Using High-Dimensional Image Models to Perform Highly Undetectable Steganography

Digital image steganography: Survey and analysis of current methods

Image quilting for texture synthesis and transfer

Image Analogies

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

An Overview of Steganography

Painter by numbers

Painter by numbers, wikiart

Jonathon Shlens

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names