Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
description [Jan 19th 2022] Paper released on arXiv. integration_instructions [Jan 14th 2022] Code released on GitHub. Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations.
https://nvlabs.github.io/instant-ngp/

Nvidia shows off AI model that turns a few dozen snapshots into a 3D-rendered scene
Nvidia latest AI demo is Instant NeRF: a model that stitches together 2D snapshots to create an impressively-detailed 3D scene. The method has been developed by other researchers, but Nvidia says it has made the process much faster and easier to implement.
https://www.theverge.com/2022/3/25/22996130/nvidia-instant-nerf-demo-ai-render-3d-scenes-2d-photos

Seonglae Cho