Weighted local regression is a promising approach to suppress undesirable noise from images generated by Monte Carlo-based rendering engines. The goal of this thesis is to test the method by implementing it into a state-of-the-art commercial rendering engine, the Corona Renderer. An essential part of the work is to investigate the robustness and performance of the method on a wide range of scenes, and propose improvements that would address its potential weak points.
Seznam odborné literatury
Bochang Moon, Nathan Carr, and Sung-Eui Yoon. 2014. Adaptive Rendering Based on Weighted Local Regression. ACM Trans. Graph. 33, 5, Article 170 (September 2014), 14 pages. DOI=http://dx.doi.org/10.1145/2641762
Bochang Moon, Jose A. Iglesias-Guitian, Sung-Eui Yoon, and Kenny Mitchell. 2015. Adaptive rendering with linear predictions. ACM Trans. Graph. 34, 4, Article 121 (July 2015), 11 pages. DOI: https://doi.org/10.1145/2766992