SOURCE-LINKED INTELLIGENCE

RoomLight: A 2.5D Illumination Prior for Indoor Environments

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Ill-posed inverse problems require priors to constrain the solution space toward plausible outcomes. In inverse rendering, learned priors modeling the distribution of natural illumination improve the recovery of scene properties. However, existing models rely on the distant-illumination assumption, representing lighting as a far-field environment map. This limits their applicability to indoor scenes, where illumination is highly spatially varying due to finite-distance emitters, visibility changes, and parallax, all of which are poorly approximated by a single environment map. To address this,

Read original source ↗ Open in workspace

recordType

paper

region

Global