Portraits of Imaginary people
Project work-in-progress from Mike Tyka creates new images of faces from a dataset using neural networks, which are then upscaled (or ‘upres-ing’) into higher resolution using machine learning methods:
For a while now I’ve been experimenting with ways to use generative neural nets to make portraits. Early experiments were based on deepdream-like approaches using backprop to the image but lately I’ve focused on GANs. As always resolution and fine detail is really difficult to achieve. For starters the receptive field of thse networks is usually less than 256x256 pixels. One way around this is tiling combined with stacking GANs ...
I tried a similar approach and I’ve been finally been having some more success upres-ing GAN-generated faces to 768x768 pixels in two stages and in some cases as far as 4k x 4k, using three stages. This gives them a lot more crisp detail. Since I’m trying to do this with art in mind, I don’t mind if the results are not necessarily realistic but fine texture is important no matter what even if it’s surreal but highres texture.
More Here
[ht Matty Mariansky]
