Image Style Transfer using Convolutional Neural Networks

Recently there has been lots of progress in the field of image style transfer, a process which aims at redrawing an image in the style of another image. Gatys et al. proposed the first approach using Convolutional Neural Networks, but their iterative algorithm is not efficient. Many others followed and improved their approach in terms of speed. This report gives an overview over various approaches for image style transfer and its extension to videos. Furthermore, their advantages and limitations will be discussed.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Andrea Vedaldi,et al.  Understanding deep image representations by inverting them , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Thomas Brox,et al.  Artistic Style Transfer for Videos , 2016, GCPR.

[5]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[7]  Andrea Vedaldi,et al.  Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Ming-Hsuan Yang,et al.  Universal Style Transfer via Feature Transforms , 2017, NIPS.

[9]  Jiaying Liu,et al.  Demystifying Neural Style Transfer , 2017, IJCAI.

[10]  Serge J. Belongie,et al.  Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).