Two Minute Papers takes a closer look at the paper “High-Resolution Daytime Translation Without Domain Labels” in this video.
Two Minute Papers dives into the paper “Analyzing and Improving the Image Quality of #StyleGAN.”
Source code is available here:- https://github.com/NVlabs/stylegan2
You can even try it.
Siraj Raval gets back to inspiring people to get into AI and pokes fun at himself.
Almost exactly 4 years ago I decided to dedicate my life to helping educate the world on Artificial Intelligence. There were hardly any resources designed for absolute beginners and the field was dominated by PhDs. In 2020, thanks to the extraordinary contributions of everyone in this community, all that has changed. It’s easier than ever before to enter into this field, even without an IT background. We’ve seen brave entrepreneurs figure out how to deploy this technology to save lives (medical imaging, automated diagnosis) and accelerate Science (AlphaFold). We’ve seen algorithmic advances (deepfakes) and ethical controversies (automated surveillance) that shocked the world. The AI field is now a global, cross-cultural movement that’s not limited to academics alone. And that’s something all of us should be proud of, we’re all apart of this. I’ve packed a lot into this episode! I’ll give my annual lists of the best ML language and libraries to learn this year, how to learn ML in 2020, as well as 8 predictions about where this field is headed. I had a lot of fun making this, so I hope you enjoy it!
Will Kwan was told he wasn’t beautiful enough to be an Instagram model so he used a generative adversarial network to generate some beautiful Instagram people to pose for me.
- StyleGAN2 (model pretrained on faces): https://github.com/NVlabs/stylegan2
- Predict the popularity of Instagram photos: https://github.com/dingkeyan93/Intrinsic-Image-Popularity
- Convert images into StyleGAN latent space to mess around with: https://github.com/michaelpdu/stylegan-encoder
Arxiv Insights shows you how to morph faces with a GAN complete with source code.
Here’s a great tutorial that uses deep learning to compose one image in the style of another image. If you’ve ever wished that you could paint like Picasso or Van Gogh. then this AI technique is your big chance.
Known as neural style transfer and the technique is outlined in A Neural Algorithm of Artistic Style, you can do this today with TensorFlow.
Neural style transfer is an optimization 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.
It acts as a kind of game that anyone can play. Visitors to the site have a choice of two images, one of which is real and the other of which is a fake generated by StyleGAN.
As to what motivated them, here’s a quote from the article:
Our aim in this course is to teach you how to think critically about the data and models that constitute evidence in the social and natural sciences.