utsavk28 / Neural-Style-Transfer

Neural style transfer is a technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.

Neural-Style-Transfer

Neural style transfer is a technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.

Theory

Types :

• Optimization Based
• Feed Forward Based

Concepts

• Adam Optimizer
• LBFGS Optimizer
• Perceptual Loss
• Instance Normalization

Results :

Type	Content Image	Style Image	Result
Random-Optimization Based
Content-Optimization Based
Random-Optimization Based
Content-Optimization Based

Todo

• Optimization Based
• Feed Forward Based

References :

Paper :

1. Origial Artistic Style NST Paper, arXiv, old
2. Orignal Artistic Style NST paper, CVPR, new
3. Perceptual Losses for Real-Time Style Transfer and Super-Resolution, arXiv

Blog :

1. Image Stylization :
   • Part 1
   • Part 2
   • Part 3
2. Style Transfer Guide

Tutorial :

1. Pytorch Tutorial
2. NST by The AI Epiphany
3. NST by Aladdin Persson

Code :

1. kanlanc NST
2. ProGamerGov NST
3. gordicaleksa NST
4. gordicaleksa NST Feed-Forward