A Compact Representation for Multiple Scattering in Participating Media using Neural Networks

Liangsheng Ge 1 Beibei Wang 2 Lu Wang 1 Nicolas Holzschuch 3
3 ARTIS - Acquisition, representation and transformations for image synthesis
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Many materials, such as milk or wax, exhibit scattering effects; incoming light enters the material and is scattered inside, giving a translucent aspect. These effects are computationally intensive as they require simulating a large number of events. Full computations are expensive, even with accelerating methods such as Virtual Ray Lights. We present a method to encode multiple scattering effects using a neural network. We replace the precomputed multiple scattering table with a trained neural network, with a cost of 6490 bytes (1623 floats). At runtime, the neural network is used to generate multiple scattering. We demonstrate the effects combined with Virtual Ray Lights (VRL), but our approach can be integrated with other rendering algorithms.
Type de document :
Communication dans un congrès
Siggraph 2018 Talks, Aug 2018, Vancouver, Canada. 〈10.1145/3214745.3214758〉
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01809890
Contributeur : Beibei Wang <>
Soumis le : jeudi 7 juin 2018 - 11:48:02
Dernière modification le : vendredi 8 juin 2018 - 01:17:19

Identifiants

Collections

IMAG | UGA | INRIA

Citation

Liangsheng Ge, Beibei Wang, Lu Wang, Nicolas Holzschuch. A Compact Representation for Multiple Scattering in Participating Media using Neural Networks. Siggraph 2018 Talks, Aug 2018, Vancouver, Canada. 〈10.1145/3214745.3214758〉. 〈hal-01809890〉

Partager

Métriques

Consultations de la notice

73

Téléchargements de fichiers

60