In this talk we will present a new artificial intelligence implementation which takes as input a 2D image and automatically reconstructs a 3D model. The reconstruction can happen in any resolution. We will also see how this same architecture combined with a generative adversarial network (GAN), similar in type to the network use for deep-fake, can be used to generate new 3D models.
We will discuss some of the challenges with 3D modelling and AI, we will present cool implementations of AI in visualization, texture analysis and 3D modelling.
This is the technical east hemisphere lecture from June 5th 2020. Attached is the PDF of the talk:
During the talk, I followed the implicit decoder research:
Open source code of the research (including trained network and datasets)
My own two blog posts about the research: