Skip to yearly menu bar Skip to main content


Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior

James Gardner · Bernhard Egger · William Smith

Hall J (level 1) #427

Keywords: [ neural fields ] [ Illumination Prior ] [ High Dynamic Range ] [ Environment Maps ] [ inverse rendering ] [ Equivariance ]


Inverse rendering is an ill-posed problem. Previous work has sought to resolve this by focussing on priors for object or scene shape or appearance. In this work, we instead focus on a prior for natural illuminations. Current methods rely on spherical harmonic lighting or other generic representations and, at best, a simplistic prior on the parameters. We propose a conditional neural field representation based on a variational auto-decoder with a SIREN network and, extending Vector Neurons, build equivariance directly into the network. Using this, we develop a rotation-equivariant, high dynamic range (HDR) neural illumination model that is compact and able to express complex, high-frequency features of natural environment maps. Training our model on a curated dataset of 1.6K HDR environment maps of natural scenes, we compare it against traditional representations, demonstrate its applicability for an inverse rendering task and show environment map completion from partial observations.

Chat is not available.