Realistic Image Synthesis using Computational Statistics

Many applications of computer graphics require accurate recreations of the appearance of the physical world. For example, computer-generated images used for product design need to be as visually close as possible to the real-world products. The most natural approach to achieve such results is computer simulation of how light interacts with given virtual shapes and materials which is called light transport simulation.

Although it is relatively not known outside the area of computer graphics, light transport simulation today heavily relies on techniques in computational statistics. In this talk, I will describe a new light transport simulation framework that is based on a novel density estimation framework, called progressive density estimation. I will also briefly talk about some other work on the intersection of computational statistics and computational statistics.