[Back]

D Scherzer, L. Yang, O. Mattausch, D. Nehab, P. Sander, M. Wimmer, E. Eisemann:
"A Survey on Temporal Coherence Methods in Real-Time Rendering";
Talk: Eurographics, Llandudno, Wales, UK; 2011-04-11 - 2011-04-15; in: "EUROGRAPHICS 2011 State of the Art Reports", Eurographics Association, 2011 (2011), 101 - 126.

Nowadays, there is a strong trend towards rendering to higher-resolution displays and at high frame rates. This development aims at delivering more detail and better accuracy, but it also comes at a significant cost. Although graphics cards continue to evolve with an ever-increasing amount of computational power, the processing gain is counteracted to a high degree by increasingly complex and sophisticated pixel computations. For real-time applications, the direct consequence is that image resolution and temporal resolution are often the first candidates to bow to the performance constraints (e.g., although full HD is possible, PS3 and XBox often render at lower resolutions).

In order to achieve high-quality rendering at a lower cost, one can exploit emph{temporal coherence} (TC). The underlying observation is that a higher resolution and frame rate do not necessarily imply a much higher workload, but a larger amount of redundancy and a higher potential for amortizing rendering over several frames. In this STAR, we will investigate methods that make use of this principle and provide practical and theoretical advice on how to exploit temporal coherence for performance optimization. These methods not only allow us to incorporate more computationally intensive shading effects into many existing applications, but also offer exciting opportunities for extending high-end graphics applications to lower-spec consumer-level hardware.

To this end, we first introduce the notion and main concepts of TC, including an overview of historical methods. We then describe a key data structure, the so-called emph{reprojection cache}, with several supporting algorithms that facilitate reusing shading information from previous frames. Its usefulness is illustrated in the second part of the STAR, where we present various applications. We illustrate how expensive pixel shaders, multi-pass shading effects, stereo rendering, shader antialiasing, shadow casting, and global-illumination effects can profit from pixel reuse. Furthermore, we will see that optimizations for visibility culling and object-space global illumination can also be achieved by exploiting TC.

This STAR enables the reader to gain an overview of many techniques in this cutting-edge field and provides many insights into algorithmic choices and implementation issues. It delivers working knowledge of how various existing techniques are optimized via data reuse. Another goal of this STAR is to inspire the reader and to raise awareness for temporal coherence as an elegant tool that could be a crucial component to satisfy the recent need for higher resolution and more detailed content.

http://publik.tuwien.ac.at/files/PubDat_200665.pdf