Bjorn Johnsson

Design and novel uses of higher-dimensional rasterization

This paper assumes the availability of a very fast higher-dimensional rasterizer in future graphics processors. Working in up to five dimensions, i.e., adding time and lens parameters, it is well-known that this can be used to render scenes with both motion blur and depth of field. Our hypothesis is that such a rasterizer can also be used as a flexible tool for other, less conventional, usage areas, similar to how the two-dimensional rasterizer in contemporary graphics processors has been used for widely different purposes other than the original intent. We show six such examples, namely, continuous collision detection, caustics rendering, higher-dimensional sampling, glossy reflections and refractions, motion blurred soft shadows, and finally multi-view rendering. The insights gained from these examples are used to put together a coherent model for what a future graphics pipeline that supports these and other use cases should look like. Our work intends to provide inspiration and motivation for hardware and API design, as well as continued research in higher-dimensional rasterization and its uses.

Efficient multi-view ray tracing using edge detection and shader reuse

Stereoscopic rendering and 3D stereo displays are quickly becoming mainstream. The natural extension is autostereoscopic multi-view displays which, by the use of parallax barriers or lenticular lenses, can accommodate many simultaneous viewers without the need for active or passive glasses. As these displays, for the foreseeable future, will support only a rather limited number of views, there is a need for high-quality interperspective antialiasing. We present a specialized algorithm for efficient multi-view image generation from a camera line using ray tracing, which builds on previous methods for multi-dimensional adaptive sampling and reconstruction of light fields. We introduce multi-view silhouette edges to detect sharp geometrical discontinuities in the radiance function. These are used to significantly improve the quality of the reconstruction. In addition, we exploit shader coherence by computing analytical visibility between shading points and the camera line, and by sharing shading computations over the camera line.

A performance and energy evaluation of many-light rendering algorithms

Recently, the performance of many-light algorithms, where thousands of light sources are used to compute the lighting in a scene, has improved so much that they have reached the realm of real-time rendering. In general, the algorithm that is considered “best” is the one that is the fastest in terms of time per frame. Given that power efficiency may become or already is one of the most important optimization factors for both hardware and software vendors for graphics, we take a different route and instead measure both energy usage per frame and frame time for a number of popular many-light rendering algorithms on an Intel Iris Pro. We use Pareto frontiers for each configuration to examine the possibilities for trade-offs between rendering time and energy consumption. Furthermore, we examine the optimal algorithms at each configuration, and are able to draw generalized conclusions on when each algorithm is most efficient. We also record several other statistics on the algorithms, e.g., bandwidth, and are able to draw further conclusions with regard to energy consumption.