Feature Fusion from Multiple Paintings for Generalized Artistic Style Transfer

6 Pages Posted: 22 Aug 2019

See all articles by Utsav Krishnan

Utsav Krishnan

Indian Institute of Technology(BHU), Students

Akshal Sharma

Indian Institute of Technology(BHU), Students

Pratik Chattopadhyay

Indian Institute of Technology (BHU) - Varanasi - Department of Computer Science & Engineering

Date Written: March 14, 2019

Abstract

The paper presents a deep CNN based artistic style transfer approach which automatically superimposes the artistic style on any input photograph. The generated image has a similar visual appearance to that of the artist’s painting(s). Existing approaches to artistic style transfer use a single painting of an artist to generate his/her painting style. We propose a more general framework in which a generalized style feature is extracted by fusing style feature from multiple paintings of an artist. A pre-trained VGG model is employed which extracts the generalized style feature from the artist’s paintings and the content feature from the input photograph. In this work, we study the different techniques for style feature fusion and present a new technique to evaluate the potency of any style transfer technique. Experimental evaluation indicates that the proposed style feature fusion technique captures the artistic style at a higher resolution than existing approaches which uses only a single painting from each artist for style transfer.

Keywords: Neural Style Transfer, Feature Fusion, VGG Network, L-BFGS Optimizer

Suggested Citation

Krishnan, Utsav and Sharma, Akshal and Chattopadhyay, Pratik, Feature Fusion from Multiple Paintings for Generalized Artistic Style Transfer (March 14, 2019). International Conference on Advances in Engineering Science Management & Technology (ICAESMT) - 2019, Uttaranchal University, Dehradun, India. Available at SSRN: https://ssrn.com/abstract=3387817 or http://dx.doi.org/10.2139/ssrn.3387817

Utsav Krishnan (Contact Author)

Indian Institute of Technology(BHU), Students ( email )

India

Akshal Sharma

Indian Institute of Technology(BHU), Students ( email )

India

Pratik Chattopadhyay

Indian Institute of Technology (BHU) - Varanasi - Department of Computer Science & Engineering ( email )

Uttar Pradesh, 221005
India

Register to save articles to
your library

Register

Paper statistics

Downloads
61
Abstract Views
264
rank
362,216
PlumX Metrics