English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Inverse rendering is an ill-posed problem. Previous work has sought toresolve this by focussing on priors for object or scene shape or appearance. Inthis work, we instead focus on a prior for natural illuminations. Currentmethods rely on spherical harmonic lighting or other generic representationsand, at best, a simplistic prior on the parameters. We propose a conditionalneural field representation based on a variational auto-decoder with a SIRENnetwork and, extending Vector Neurons, build equivariance directly into thenetwork. 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 acurated dataset of 1.6K HDR environment maps of natural scenes, we compare itagainst traditional representations, demonstrate its applicability for aninverse rendering task and show environment map completion from partialobservations. A PyTorch implementation, our dataset and trained models can befound at jadgardner.github.io/RENI.

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