News for hackers. Stuff that matters.
Re:Scalable Large Scene Neural View Synthesis by krasin on Friday February 11, 2022 @09:14PM (#30309279)
This is using Neural Radiance Fields (aka NeRF) that first appeared about two years ago: https://www.matthewtancik.com/nerf

Originally, it took more than 1 GPU-week to train a single static scene. After multiple rounds of algorithmic optimizations, it's now practical to train & render whole city blocks, as seen in the Waymo demo.

The best part of it, is the answer to the classic question: "how many polygons?". Because the answer is zero.

Re:Scalable Large Scene Neural View Synthesis by WithinReason on Saturday February 12, 2022 @06:04AM (#30311824)
These guys train representations for some scenes in seconds:

https://nvlabs.github.io/instant-ngp/