NeRF

Neural Radiance Fields, a technique for synthesizing novel 3D views from 2D images by training neural networks to represent scenes as continuous volumetric functions.

NeRF (Neural Radiance Fields) is a 2020 breakthrough in 3D scene representation that uses neural networks to encode scenes as continuous functions mapping 3D coordinates to color and density values. Given a sparse set of 2D images, NeRF can render photorealistic novel views of a scene from any angle. The technique enables converting ordinary video footage into navigable 3D representations, providing abundant training data for world models.

Also known as