GPU-Accelerated Monte Carlo Geometry Processing for Gradient-Domain Methods

Sammanfattning: This thesis extends the utility of the Monte Carlo approach to PDE-based methods presented in the paper Monte Carlo Geometry Processing. In particular, we implement this method on the GPU using CUDA, and investigate more viable methods of estimating the source integral when solving Poisson’s equation with intricate source terms. This is the case for a large group of gradient-domain methods in computer graphics, where source terms are represented by discrete volumetric data on regular grids. We develop unbiased source integral estimators like image-based importance sampling (IBIS) and biased estimators like source integral caching (SIC) and evaluate these against existing GPU-accelerated finite difference solvers for gradient-domain applications. By decoupling the source integration step from the WoS-algorithm, we find that the SIC method can improve performance by several orders of magnitude, making it competitive with existing finite difference solvers in many cases. We further investigate the viability of distance fields for accelerated distance queries and find that these can provide significant performance improvements compared to BVHs without meaningfully affecting bias.