When will ray-tracing replace rasterization?
ACM SIGGRAPH 2002 conference abstracts and applications on - SIGGRAPH '02
Motivation Ray-tracing produces images of stunning quality but is difficult to make interactive. Rasterization is fast but making realistic images with it requires splicing many different algorithms together. Both GPU and CPU hardware grow faster each year. Increased GPU performance facilitates new techniques for interactive realism, including high polygon counts, multipass rendering, and texture-intensive techniques such as bumpmapping and shadows. On the other hand, increased CPU performance
... nd dedicated ray-tracing hardware push the potential framerate of ray-tracing ever higher. Depth-buffering rasterization made scanline geometric hiddenline techniques obsolete because it was easy to implement and dropping memory prices made implementations affordable, even though Sutherland, et al., concluded it was hopelessly inefficient. Question for the Panel Will the simplicity and/or increasing performance of ray-tracing make rasterization obsolete, and when? Speakers will address the future of rasterization versus ray-tracing/ray-casting techniques based on their broad and diverse industry experience and individual viewpoints as leaders in the graphics community. Kurt Akeley Rasterization hardware and the associated graphics standards, such as Direct 3D and OpenGL, will be around for a long time. Ray tracing will become feasible, outside of niche markets serviced with custom hardware, only as it can be implemented using rasterization hardware infrastructure. Because rasterization hardware is advancing in performance, flexibility, and programmability so rapidly, we can expect dramatic improvements in the image quality of interactive systems during the next few years. Applications will introduce ray tracing algorithms gradually, synthesizing rasterization, ray tracing, and other global shading techniques to obtain the best overall results. Kurt Akeley works part time at NVIDIA Corporation, where he is a member of the graphics architecture team. He spends the rest of his week at Stanford, working toward the completion of the electrical engineering Ph.D. that he put on hold in 1982 to co-found Silicon Graphics. During his 19 years at Silicon Graphics Kurt lead the development of several high-end graphics systems, including GTX, VGX,