RoomLight: A 2.5D Illumination Prior for Indoor Environments

This repository contains the model presented in RoomLight: A 2.5D Illumination Prior for Indoor Environments.

• Project page: https://andreead-a.github.io/RoomLight
• Code: https://github.com/andreead-a/RoomLight

RoomLight is a spatially-aware illumination prior trained on real-world indoor panoramas and their estimated depth. The variational autoencoder model learns a compact, optimizable latent space that decodes into HDR radiance and depth, parameterizing an area light emitter for direct integration into standard differentiable rendering pipelines.