Today we're joined by Josh Tobin, Co-organizer of the machine learning training program Full Stack Deep Learning, and more recently, the founder of a stealth startup.
We had the pleasure of sitting down with Josh prior to his presentation of his paper Geometry-Aware Neural Rendering, which looks to build upon DeepMind's "Neural scene representation and rendering," with the goal up developing implicit scene understanding. In our conversation, we discuss the challenges his paper seeks to address, how he was able to pull from three different datasets to train his model, and the similarities between variational autoencoder training and his process.
