A Compact Representation for Multiple Scattering in Participating Media using Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (2) , (1) , (3)
1
2
3
Beibei Wang
Lu Wang
  • Function : Author
  • PersonId : 873867

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.
Fichier principal
Vignette du fichier
nnRender_final.pdf (2.12 Mo) Télécharger le fichier
Vignette du fichier
Figure1.jpg (60.58 Ko) Télécharger le fichier
Vignette du fichier
Figure2.jpg (56.78 Ko) Télécharger le fichier
Vignette du fichier
Figure3.jpg (107.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01809890 , version 1 (07-06-2018)

Identifiers

Cite

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. pp.1-2, ⟨10.1145/3214745.3214758⟩. ⟨hal-01809890⟩
998 View
353 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More