No abstract

Polygon rasterization is the most computational and memory intense stage in rendering synthesized computer images. I n this paper, we present a low-power, real-time hardware implementation for this task. Rasterization of two-dimensional, Gourad-shaded polygons at 90.000 polygonslsec is achievable with computational power consumption of about I2 mW at I J V operation, using an array configuration of I6 render engines for a 512xS12-pixel frame. A transmission format for wireless implementations is proposed with a typical bandwidth of 4 MHz. This screen and format configurable design has potential applications in portable devices, wireless communication and head-mounted dkplay for virtual realiry systems.

Abstract. Polygon rasterization is one of the most computational and memory intensive operations in computer graphics. In this paper, we present a low-power, real-time hardware design for this task. The system is resolution-independent by configuring different numbers of render engines in a 2-dimensional array. Using an array configuration of 16 render engines for a 512 x 512-pixel display, a peak performance of up to 3.4 million Gouraud-shaded polygons/sec is achievable. Total power consumption, depending on the polygon throughput, ranges between 17 mW to 133 mW at 1.5 V operation. A format for transmitting polygon information is proposed at a typical bandwidth of 4 Mbps, suitable for wireless transmission. This screen and format configurable design has potential application in portable, wireless head-mounted displays for virtual reality systems.

In many color-imaging applications, it is desirable to display an image with as few different colors as possible with minimal loss in image quality. While good image quality is achievable using traditional Vector Quantization techniques. they are too slow for real-time vidm applications. An architectural design of a real-time, scalable color quantizer architecture is presented. It implements our fast Tree Structure Vector Quantization algorithm with a variable-size cubical prequantizer based on human perception proposed earlier. The design is scalable and uses different configurations of the processing and memory elements to process any 24-bit to 72-bit colors per input pixel to produce a 8-bit to 24-bit color palette.