I've been working on implementing this too! It's been fun trying to debug problems by figuring out how to reduce it to the "bare minimum" to repro. Ex: does it work if I disable positional encoding? Does it work if I have only one sample per ray on a single image dataset? Etc
> Enabled by a joint design of the camera’s hardware and computational processing, the system could enable minimally invasive endoscopy with medical robots to diagnose and treat diseases, and improve imaging for other robots with size and weight constraints. Arrays of thousands of such cameras could be used for full-scene sensing, turning surfaces into cameras.
There are existing swallowable capsule endoscopy devices like the PillCam[1], the entirety of which is 11mm x 26mm[2]
Looking for opportunities in scientific computing, geometry processing, graphics, computer vision, and/or machine learning. I have over 3 years of experience working on problems in scientific computing, deep learning, backend engineering, physics simulations, and graphics at startups and research labs.
The Game Engine Black Book by Fabien Sanglard[1] is a wonderful book that talks about some of the engineering challenges and tricks employed by id software to get Wolfenstein 3D working.