Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

neural radiance field (NeRF)

An implicit scene representation -- a trained network that outputs color and density for any 3D point and viewing direction, enabling novel-view rendering.

A neural radiance field (NeRF) represents a 3D scene implicitly as a trained network mapping a 3D point and a viewing direction to a color and density, rendered into a novel view by integrating these values along camera rays -- an implicit, continuous scene representation, as opposed to Gaussian Splatting's explicit, discrete one.

Examples

  • A NeRF trained on 50 photos of a statue can render a brand-new view from an angle none of the original photos captured, by querying its trained network along new camera rays.

Read the full section →
Graph settings

Calculator