# VENI: Variational Encoder for Natural Illumination

Source: [VENI: Variational Encoder for Natural Illumination](<https://www.sota2.com/research/paper/69705de8e25ad2fa9d1ed78f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-26T05:00:04.994Z

Authors: Paul Walker, James A. D. Gardner, Andreea Ardelean, William A. P. Smith, Bernhard Egger

Published: 2026-01-20T15:38:02.000Z

## Abstract

Inverse rendering is an ill-posed problem, but priors such as illumination priors can help simplify it. Existing work either disregards the spherical and rotation-equivariant nature of illumination environments or does not provide a well-behaved latent space. We propose a rotation-equivariant variational autoencoder that models natural illumination on the sphere without relying on 2D projections. To preserve the SO(2)-equivariance of environment maps, we use a novel Vector Neuron Vision Transformer (VN-ViT) as encoder and a rotation-equivariant conditional neural field as decoder. In the encoder, we reduce the equivariance from SO(3) to SO(2) using a novel SO(2)-equivariant fully connected layer, an extension of Vector Neurons. We show that our SO(2)-equivariant fully connected layer outperforms standard Vector Neurons when used in our SO(2)-equivariant model. Compared to previous methods, our variational autoencoder enables smoother interpolation in latent space and offers a more well-behaved latent space.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Reconstruction on StreetLearn HDR converted (test)](<https://www.sota2.com/research/sota/reconstruction-on-streetlearn-hdr-converted-test.md>): Reconstruction; StreetLearn HDR converted (test); PSNR: 22.68.

- [Latent Space Analysis on StreetLearn converted (test)](<https://www.sota2.com/research/sota/latent-space-analysis-on-streetlearn-converted-test.md>): Latent Space Analysis; StreetLearn converted (test); Uniqueness: 0.57.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.14079>)

[PDF](<https://arxiv.org/pdf/2601.14079.pdf>)
