Active Exploration for Neural Global Illumination of Variable Scenes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles ACM Transactions on Graphics Year : 2022

Active Exploration for Neural Global Illumination of Variable Scenes


Neural rendering algorithms introduce a fundamentally new approach for photorealistic rendering, typically by learning a neural representation of illumination on large numbers of ground truth images. When training for a given variable scene, i.e., changing objects, materials, lights and viewpoint, the space D of possible training data instances quickly becomes unmanageable as the dimensions of variable parameters increase. We introduce a novel Active Exploration method using Markov Chain Monte Carlo, which explores D, generating samples (i.e., ground truth renderings) that best help training and interleaves training and on-the-fly sample data generation. We introduce a self-tuning sample reuse strategy to minimize the expensive step of rendering training samples. We apply our approach on a neural generator that learns to render novel scene instances given an explicit parameterization of the scene configuration. Our results show that Active Exploration trains our network much more efficiently than uniformly sampling, and together with our resolution enhancement approach, achieves better quality than uniform sampling at convergence. Our method allows interactive rendering of hard light transport paths (e.g., complex caustics) -- that require very high samples counts to be captured -- and provides dynamic scene navigation and manipulation, after training for 5-18 hours depending on required quality and variations.
Fichier principal
Vignette du fichier
active-exploration.pdf (38.57 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03594357 , version 1 (02-03-2022)



Stavros Diolatzis, Julien Philip, George Drettakis. Active Exploration for Neural Global Illumination of Variable Scenes. ACM Transactions on Graphics, In press, ⟨10.1145/3522735⟩. ⟨hal-03594357⟩
81 View
10 Download



Gmail Mastodon Facebook X LinkedIn More