Viet-Anh on Software Logo

What is: Neural Radiance Field?

SourceNeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

NeRF represents a scene with learned, continuous volumetric radiance field FθF_\theta defined over a bounded 3D volume. In a NeRF, FθF_\theta is a multilayer perceptron (MLP) that takes as input a 3D position x=(x,y,z)x = (x, y, z) and unit-norm viewing direction d=(dx,dy,dz)d = (dx, dy, dz), and produces as output a density σ\sigma and color c=(r,g,b)c = (r, g, b). The weights of the multilayer perceptron that parameterize FθF_\theta are optimized so as to encode the radiance field of the scene. Volume rendering is used to compute the color of a single pixel.