A characterization of ten rasterization techniques
SIGGRAPH '89 Proceedings of the 16th annual conference on Computer graphics and interactive techniques
On temporal-spatial realism in the virtual reality environment
UIST '91 Proceedings of the 4th annual ACM symposium on User interface software and technology
PixelFlow: high-speed rendering using image composition
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
A Sorting Classification of Parallel Rendering
IEEE Computer Graphics and Applications
Priority rendering with a virtual reality address recalculation pipeline
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Improving static and dynamic registration in an optical see-through HMD
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
I3D '95 Proceedings of the 1995 symposium on Interactive 3D graphics
Real-time programmable shading
I3D '95 Proceedings of the 1995 symposium on Interactive 3D graphics
Predictive tracking for augmented reality
Predictive tracking for augmented reality
The triangle processor and normal vector shader: a VLSI system for high performance graphics
SIGGRAPH '88 Proceedings of the 15th annual conference on Computer graphics and interactive techniques
SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
| Hi-index | 0.00 |
Performance, as measured by the number of primitives rendered per second, has been the most important rendering system design consideration while latency, the amount of time it takes to render an image, has largely been ignored. This is because a moderate amount of latency is not an issue for traditional interactive systems controlled by joysticks. However, latency has emerged as a major consideration when rendering for immersive systems, especially those using head-mounted displays. Maintaining low overall system latency is very important to create an illusion of presence in a virtual environment and very significant contribution to total system latency is the time it takes to generate an image. This paper examines some possible ways to reduce latency in the PixelFlow graphics computer. We first describe the standard rendering software for PixelFlow, and derive an expression for the time to render an image. We then propose two alternative software systems for the PixelFlow hardware, and derive expressions for the rendering latency. When we compare latencies for some common application scenarios, we find that the two propsed systems render with lower latency than the standard highthroughput system, but find that the benefits are not enough to outweigh the costs.