Rethinking Style Transfer: From Pixels to Parameterized Brushs | Gradient Dude
Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
[Another recent "style transfer with brushstrokes" paper from my colleagues in Heidelberg University ]
In this paper, images are stylized by optimizing parameterized brush strokes instead of pixels as well. In order to backpropagate teh error through the rendered brushstrokes, the authors came up with a simple differentiable rendering of strokes, each of which is parameterized with a Bezier curve.
The results are excellent. You can also add constraints to the shape of your brush strokes by drawing a couple of lines over the photo. The only drawback is that it works for a rather long time (10-20 minutes per 1MP picture), since this is an iterative optimization, and at each iteration a forward-pass through VGG-16 newtwork is required.
TL;DR for DL/CV/ML/AI papers from an author of publications at top-tier AI conferences (CVPR, NIPS, ICCV,ECCV). Most ML feeds go for fluff, we go for the real meat. YouTube: youtube.com/c/gradientdude...
