Computational Decomposition of Style for Controllable and Enhanced Style Transfer

11/21/2018
by   Minchao Li, et al.
2

Neural style transfer has been demonstrated to be powerful in creating artistic image with help of Convolutional Neural Networks (CNN). However, there is still lack of computational analysis of perceptual components of the artistic style. Different from some early attempts which studied the style by some pre-processing or post-processing techniques, we investigate the characteristics of the style systematically based on feature map produced by CNN. First, we computationally decompose the style into basic elements using not only spectrum based methods including Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT) but also latent variable models such Principal Component Analysis (PCA), Independent Component Analysis (ICA). Then, the decomposition of style induces various ways of controlling the style elements which could be embedded as modules in state-of-the-art style transfer algorithms. Such decomposition of style brings several advantages. It enables the computational coding of different artistic styles by our style basis with similar styles clustering together, and thus it facilitates the mixing or intervention of styles based on the style basis from more than one styles so that compound style or new style could be generated to produce styled images. Experiments demonstrate the effectiveness of our method on not only painting style transfer but also sketch style transfer which indicates possible applications on picture-to-sketch problems.

READ FULL TEXT

page 7

page 11

page 12

page 16

page 17

page 18

page 19

page 20

research
02/27/2019

StyleRemix: An Interpretable Representation for Neural Image Style Transfer

Multi-Style Transfer (MST) intents to capture the high-level visual voca...
research
05/11/2017

Neural Style Transfer: A Review

The recent work of Gatys et al. demonstrated the power of Convolutional ...
research
11/30/2018

Style Decomposition for Improved Neural Style Transfer

Universal Neural Style Transfer (NST) methods are capable of performing ...
research
11/23/2016

Controlling Perceptual Factors in Neural Style Transfer

Neural Style Transfer has shown very exciting results enabling new forms...
research
08/10/2019

Channel Decomposition on Generative Networks

This work presents a method to decompose a layer of the generative netwo...
research
03/19/2015

Interactive Illustrative Line Styles and Line Style Transfer Functions for Flow Visualization

We present a flexible illustrative line style model for the visualizatio...
research
05/28/2018

Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

In this paper, we introduce an unsupervised learning approach to automat...

Please sign up or login with your details

Forgot password? Click here to reset