Projects Last Projects

Next Generation Image Style Transfer via CNN

Adar Elad & Mark Erlich

Supervised by Alona Golts

Abstract

Image Style Transfer refers to an artistic process in which a content image is modified to include the style taken from a second image. Early signs of this idea appeared in the early 2000's, but the real breakthrough came with the impressive work of Leon Gatys and his co-authors. Their method relies on pre-learned neural networks, that has been trained for image recognition. Our project focuses on expanding and improving the prime weaknesses of Gatysâ€™ algorithm: (i) preservation of edges; (ii) enabling treatment of large images; and (iii) speeding up the whole transfer process

Pictures

Project Next Generation Image Style Transfer via CNN Picture 1

Project Next Generation Image Style Transfer via CNN Picture 2

Project Next Generation Image Style Transfer via CNN Picture 3

Project Next Generation Image Style Transfer via CNN Picture 4

Project Next Generation Image Style Transfer via CNN Picture 5

Project Next Generation Image Style Transfer via CNN Picture 6