Incredible, I love this so much. I'm glad someone out there decides to go make older games like this in newer engines. Great work!
Firstly,Amazing work !! But a doubt..for the background thing ..you mentioned of using a mesh with zero edges which helps out in covering up the repetition process..what is it?..any detailed description please.
Quite fantastic. I am a friend of Grayson Wixom and have an entertainment publication thehollywoodtimes.today and am trying to get one of my journalists to interview you.
Have a look at a rather new training methodology for generative adversarial networks by a team of researchers from Nvidia.
The key idea here is to grow both the generator and discriminator progressively: “starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024²,” states the team.
The team also proposes a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, they described several implementation details that are important for discouraging unhealthy competition between the generator and discriminator.
Finally, they suggest a new metric for evaluating GAN results, both in terms of image quality and variation.
You can learn more and find the full paper here.