I am very impressed! It is easy to see you are on your way to a well-deserved wonderful future.
An absolutely great read, thank you for this. Really lays a foundation on how to go about the learning process.
Hi Matthew and Mr VFX, I’m currently researching this topic of decomposing images into shading and reflectance layers. I would love to learn about what you are trying to use this for to learn more about applications for this technology.
The portraits you see below are actually fake. They were completely generated by AI, so none of these people actually exist.
NVIDIA researchers have recently presented a new paper on customizing the style of realistic faces created by a generative adversarial network (GAN). It is worth pointing out that whole GAN thing has only existed for four years starting with this landmark paper in 2014.
As of this moments, it had to define whether the portraits are fake, even when examining them in detail.
NVIDIA researchers can now copy the “styles” of source faces onto destination faces, creating new images which look like entirely new people.
To create these latest faces, NVIDIA researchers trained the AI for a whole week using 8 powerful GPUs. Here’s a 6-minute video about this latest progress:
There’s actually more to the story. The tech can also generate other kinds of stuff. Check out some examples below.
Make sure to discuss the news in the comments below.