A radiance field is a function that describes how much light — color and intensity — travels in every direction through every point in a 3D space. Capturing this field lets a renderer reproduce how a scene looks from any viewpoint, including view-dependent effects like reflections and highlights.
Radiance fields can be stored as a neural network, as in neural radiance fields, or as explicit primitives, as in Gaussian splatting. Both encode the same idea — a continuous description of scene appearance — and differ mainly in how they are represented and rendered.
Neural radiance fields (NeRFs) — Radiance fields encoded in neural network weights.
Gaussian splatting — Radiance fields represented as explicit 3D Gaussians.
Novel view synthesis — What radiance fields make possible.
Streaming video reshaped media consumption; we're doing the same for 3D. Join a small team solving tough spatial streaming, content delivery, and developer experience challenges.
Technical deep-dives on adaptive spatial streaming, the infrastructure challenges of 3D at scale, and what we're learning as we build. Written by the team doing the work.
