Lightweight Bilateral Convolutional Neural Networks for Interactive Single-Bounce Diffuse Indirect Illumination

Physically correct, noise-free global illumination is crucial in physically-based rendering, but often takes a long time to compute. Recent approaches have exploited sparse sampling and filtering to accelerate this process but still cannot achieve interactive performance. It is partly due to the tim...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on visualization and computer graphics 2022-04, Vol.28 (4), p.1824-1834
Hauptverfasser:	Xin, Hanggao, Zheng, Shaokun, Xu, Kun, Yan, Ling-Qi
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Coherence global illumination Illumination Lattices Lighting Lightweight Monte Carlo methods Neural networks Real-time rendering Rendering (computer graphics) Sampling Three-dimensional displays
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!