Advanced Denoising and Memoryless Acceleration for Realistic Image Synthesis

Abstract

Stochastic ray tracing methods have become the industry's standard for today's realistic image synthesis thanks to their ability to achieve a supreme degree of realism by physically simulating various natural phenomena of light and cameras (e.g. global illumination, depth-of-field, or motion blur). Unfortunately, high computational cost for more complex scenes and image noise from insufficient simulations are major issues of these methods and, hence, acceleration and denoising are key components in stochastic ray tracing systems. In this thesis, we introduce two new filtering methods for advanced lighting and camera effects, as well as a novel approach for memoryless acceleration. In particular, we present an interactive filter for global illumination in the presence of depth-of-field, and a general and robust adaptive reconstruction framework for high-quality images with a wide range of rendering effects. To address complex scene geometry, we propose a novel concept which models the acceleration structure completely implicit, i.e. without any additional memory cost at all, while still allowing for interactive performance. Our contributions advance the state-of-the-art of denoising techniques for realistic image synthesis as well as the field of memoryless acceleration for ray tracing systems.