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 MAVERICK - Models and Algorithms for Visualization and Rendering
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01809890
Contributor : Beibei Wang <>
Submitted on : Thursday, June 7, 2018 - 11:48:02 AM
Last modification on : Sunday, September 23, 2018 - 6:26:57 PM
Long-term archiving on : Saturday, September 8, 2018 - 1:18:22 PM

Identifiers

Collections

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. pp.1-2, ⟨10.1145/3214745.3214758⟩. ⟨hal-01809890⟩

Share

Metrics

Record views

1249

Files downloads

576