||Efficient realistic image synthesis is important for a number of applications, ranging from feature film production over computer games to everyday applications like geo-visualization. We seek to synthesize high-fidelity imagery as currently found in movie productions that take considerable effort and time to produce using common graphics hardware found on everyday devices of varying capabilities. To this end, we are committed to devise new rendering techniques, which blend the traditional distinction between offline and interactive image synthesis. Our particular interest here is efficient global illumination, its approximate solution and the exploitation of modern, massively parallel graphics hardware (GPU). Global illumination generalizes the commonly made assumption of point lights directly illuminating a scene to more complex light transport involving multiple reflections. The challenge of simulating indirect light involving complex dynamic geometry and complex dynamic materials is still an open problem and we try to make the right approximations that will allow attacking the problem using modern massively parallel architectures, such as GPUs.
Further, the two interfaces of rendering - artists that provide media and humans consuming them - are included in our research. We support artists in their challenge to achieve a certain goal, both by providing new tools for effective artistic manipulation on "their side" of the interface, or by re-thinking how rendering should be done "on our side" (Non-photorealistic rendering). Considering human perception in the design of algorithms can improve both the user experience on "his" side of the interface, as well as efficiency of algorithms on "our" side by making perceptually valid approximations.
Tobias Ritschel joined University College of Londen in fall 2015.