Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method Qihang Fang 1,2,* Y afei Song 3,* Keqiang Li

A neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly.