NeRF: Representing Scenes as Neural Radiance…

NeRF learns one continuous, scene-specific function of 3D position and viewing direction, then volume-renders that function into new camera views. Read it to see how density controls both color and visibility along a ray, why sinusoidal coordinates and hierarchical sampling matter, and where the original method trades speed for fidelity.

Reading focus: How position-dependent density and view-dependent color represent one static scene. Why transmittance and opacity turn ordered ray samples into a differentiable pixel color. What the main result, component ablations, per-scene optimization, and rendering cost actually establish.

ECCV 2020. Ben Mildenhall et al.. 30 min read, medium difficulty.