Realistic Real-Time Rendering of Global Illumination and Hair through Machine Learning Precomputations
In general, machine learning and neural network methods are not designed to run at the speeds that are required for rendering in high-performance real-time environments, except for very specific and typically limited uses. For example, several methods have been developed recently for denoising of low quality pathtraced images, or to upsample images rendered at lower resolution, that can run in real-time.
This thesis collects two methods that attempt to improve realistic scene rendering in such high-performance environments by using machine learning.
Paper I presents a neural network application for compressing surface lightfields into a set of unconstrained spherical gaussians to render surfaces with global illumination in a real-time environment.
Paper II describes a filter based on a small convolutional neural network that can be used to denoise hair rendered with stochastic transparency in real time.
Roc Ramon Currius
Embedded Electronics Systems and Computer Graphics
Spherical Gaussian Light‐field Textures for Fast Precomputed Global Illumination
Computer Graphics Forum,; Vol. 39(2020)p. 133-146
Artikel i vetenskaplig tidskrift
R. Currius, Roc, Assarsson, Ulf, Sintorn, Erik. Real-Time Hair Filtering with Convolutional Neural Networks
Komprimering av förberäknad belysningsinformation
Vetenskapsrådet (VR) (2017-05060), 2018-01-01 -- 2021-12-31.
Fotorealistisk rendering för realtid
Vetenskapsrådet (VR) (2014-4559), 2014-01-01 -- 2021-12-31.
Technical report L - Department of Computer Science and Engineering, Chalmers University of Technology and Göteborg University
Opponent: Leonardo Scandolo, Delft University of Technology, Netherlands