Abstract: We describe PixelFlow, an architecture for high-speed image generation that overcomes the transformationand frame-buffer– access bottlenecks of conventional hardware rendering architectures. PixelFlow uses the technique of image composition: it distributes the rendering task over an array of identical renderers, each of which computes a fill-screen image of a fraction of the primitives. A high-performance image-composition network composites these images in real time to produce an image of the entire scene. Image-composition architectures offer performance that scales linearly with the number of renderers; there is no fundamental limit to the maximum performance achievable using this approach. A single PixelFlow renderer rasterizes up to 1.4 million triangles per second, and an n-renderer system can rasterize at up to n times this basic rate. PixelFlow performs antialiasing by supersampling. It supports defemed shading with separate hardware shaders that operate on composite images containing intermediate pixel data. PixelFlow shaders compute complex shading algorithms and procedural and image-based textures in real-time. The shading rate is independent of scene complexity. A Pixel Flow system can be coupled to a parallel supercomputer to serve as an immediatemode graphics server, or it can maintain a display list for retainedmode rendering. The PixelFlow design has been simulated extensively at high level. Custom chip design is underway. We anticipate a working system by late 1993. CR

Abstract: This comprehensive work merges two of the hottest topics in computer science: parallel computing and computer graphics. Selected Topics from the Table of Contents: -Overview of Accelerated Rendering Techniques -Overview of Parallel Methods for Image Generation -Issues in Parallel Algorithm Development -Overview of Base Level Implementation -Comparison of Task Partitioning Schemes -Characterization of Other Parameters on Performance

Abstract: Surface-particles are very small facets, modeled as points with a normal. They can be used to visualize flow in several ways by variation of the properties of the particle sources. Here a new method is presented for the rendering of surface-particles. This method includes an improved shading model, the use of Gaussian filters for the prevention of spatial and temporal artifacts, an efficient scan-conversion algorithm, the handling of occlusion and the simultaneous rendering of geometric objects and surface-particles. The synthesis of images with limited depth of field is described, which literally allows the scientist to focus on areas of interest.

Abstract: Graphics window systems which utilize graphics pipelines and graphics pipeline bypass buses. Hardware solutions for window relative rendering of graphics primitives, block moving of graphics primitives, transfer of large data blocks, and elimination of pipeline flushing are disclosed. The hardware implementations provided in accordance with the invention are interfaced along the pipeline bypass bus, thereby eliminating gross overhead processor time for the graphics pipeline and reducing pipeline latency. Methods and apparatus provided in accordance with the invention exhibit significant pipeline efficiency and reductions in time to render graphics primitives to the screen system.

Abstract: Direct volume rendering is a computationally intensive operation that has become a valued and often preferred visualization tool. For maximal data comprehension, interactive manipulation of the rendering parameters is desirable. To this end, a reasonable target would be a system capable of displaying 1283 voxel data sets at multiple frames per second. Although the computing resources required to attain this performance are beyond those available in current uniprocessor workstations, multicomputers and VLSI rendering hardware offer a solution. This paper describes a volume rendering algorithm for MIMD message passing multicomputers. This algorithm addresses the issues of distributed rendering, data set distribution, load balancing, and contention for the routing network. An implementation on a multicomputer with a 1D ring network is analyzed, and extension of the algorithm to a 2D mesh topology is described. In addition, the paper presents a method of exploiting screen coherence through the use of VLSI pixel processor arrays. Though not critical to the general algorithm, this rendering approach is demonstrated in the example implementation where it serves as a hardware accelerator of the rendering process. Commercial graphics workstations use pixel processors to accelerate polygon rendering; this paper proposes a new use of this hardware for accelerating volume rendering. 1 . Introduction Direct volume rendering is the common name that describes the viewing of volume data as a semi-transparent cloudy material. Its advantages are that much or all of the volume may be visible to the observer at one time; there is no need to introduce intermediate geometry that doesn't really exist in the data. We assume the input data is a scalar field sampled at the vertices of a 3D rectilinear lattice a situation often encountered in medical and simulation data. Plate 1 is an image of a representative medical data set of dimensions 128x128x124. The following 3-step conceptual model of the volume rendering process is based on previously published derivations [Blinn82] [Kajiya+84]. Much of this example comes from Wilhelms and Gelder [Wilhelms+91]. 1 Reconstruct the continuous 3D scalar function F by convolving each sample point f with a reconstruction filter kernel K. F(x,y,z) = f x,y,z * K ∑ x,y,z 2 Apply an opacity O and shading S function to the continuous scalar field. These user definable transfer functions yield a differential opacity Ω = O(F) and color emittance E = S (F) at each point in the volume as a function of the scalar field properties at that point. The Ω and E fields should then be low-pass filtered for resampling in the next step. 3 Integrate an intensity and transparency function along sample view-ray paths through the volume. The integrals may be taken toward or away from the viewer. When taken towards the viewer, the accumulated intensity I and transparency T along the sample ray is I(p) = T(p) E(v) T(v) dv

Abstract: Hardware logic and processing methods for enhanced data manipulation within a graphics display system are described. The graphics display system includes a graphics processor sub-system and a rendering subsystem which are serially connected for pipeline processing of an interleaved stream of commands and data. One or more status bits or XBITs are defined within each rasterizer of a multi-rasterizer rendering sub-system. An XBIT, which may comprise a ZBIT, a UBIT, or an RBIT, etc., provides a mechanism for introducing execution of various logic functions within the rendering sub-system portion of the computer graphics adapter. Corresponding data processing methods are also described.

Abstract: Recently, there has been increasing interest in the design of user interfaces that take advantage of graphics when presenting information. Since it is impossible to anticipate the needs and requirements of each potential user in an infinite number of presentation situations, it is more reasonable to automatically design graphics on the fly in a context-sensitive way. In this paper, we present components for graphics design and graphics realization as parts of the multimodal presentation system WIP. After a short overview of WIP, we introduce our basic assumptions about how to describe surface aspects and the meaning of complex graphics. We then describe the graphics realization component and sketch the graphics design process. By means of a generation example we show graphics design is interleaved with graphics realization.

Abstract: A computer graphics course is extremely hardware system dependent, even more than most computer science courses. To produce high quality graphics images requires a high resolution system with extensive color capability and a fast cpu. Fortunately, the computer graphics capabilities of inexpensive systems have continued to increase. As this trend continues we need to consider changing the way we teach our computer graphics courses. In this paper I discuss a major shift in my teaching methods in the past year. Whereas, previously my students developed their own programs to create images, I have switched to the use of the Pixar RenderMan graphics package in the second graphics course and use it at the end of the first graphics course. I will discuss the rational for this change, mine and the students' experiences with it, and future planned modifications of the courses.

Abstract: The addition of graphics-specific features to the series 700 system architecture has improved graphics performance by 33% to 100% across various graphics workloads relative to the base system architecture. The model 730, which incorporates a 76 SPECmark PA-RISC (reduced instruction set computer) CPU, is capable of rendering over 1,000,000 3D vectors/s and 19400 independently shaded, z-buffered quadrilaterals/s using a simple entry level frame buffer. Further improvements in performance may be obtained by partitioning the graphics pipeline between the CPU and dedicated rasterization and geometry accelerators. Enhancements to the CPU include polygon rasterization with virtual memory z-buffer support, graphics-specific floating-point, and graphics-specific data path features. >

Abstract: GraphPak - A 2D Graphics Class Library Object Graphics Implementing GEO++ in Smalltalk-80 GOII - An Object-Oriented Framework for Computer Graphics The Graphical Application Support System Object-Oriented Programming in Computer Graphics - ALPHA 1, A Case Study An Object-Oriented Approach to Animation Control Object-Oriented Graphics for Interactive Visualization of Distributed Scientific Computations IDA - An Interactive Data Display System Object-Oriented Ray Tracing - A Comparison of C++ Versus C Implementations Design of a Mathematician's Drawing Program.

Abstract: Traditional graphics systems have tightly coupled the modeling and rendering sub-systems in order to maximize efficiency. In addition, object modeling has been done so that the data is readily understood by the renderers. Some systems provide sophisticated rendering capabilities but do so at the expense of user understandability. The results have been systems that are difficult to extend and that force users to interact with the graphics system at a very low level of abstraction. While many of these systems are capable of producing near-photorealistic images, the complexity involved in doing so is beyond the scope of the novice user. GRAMS, the GRaphical Application Modeling Support system, is an general object-oriented 3D graphics system designed to overcome many of the deficiencies of current systems. GRAMS is comprised of three main components--the application, graphics, and rendering layers. The application user defines data at the application layer. The graphics system extracts pertinent data from the application layer, interprets that data in a semantically correct fashion, transforms the data into a form understandable by the renderers, then sends the data to the renderers. The rendering layer then performs the actual image generation. By structuring the system in this fashion and by capitalizing on the benefits of object-orientation, the application is allowed to work at a high level of abstraction without concern for low-level graphics or rendering details. In addition to providing a mechanism for raising the abstraction level at which the application interfaces with the graphics system, GRAMS is also designed to be easily extensible. The interfaces between layers of the system have been defined such that new capabilities can be added at any system level without making alterations to other levels. Through inter-object communication the system optimizes data transformations and allows system components to utilize efficiencies inherent to them.

Abstract: The verification of identifying and pose hypotheses in model-based 3D object recognition systems can involve a time-consuming image rendering operation followed by pixel-level comparison of the input and rendered images. In situations where many such hypotheses need to be verified, exploitation of inherent data-parallelism between hypotheses and their corresponding object models can increase the efficiency of the object recognition system. The authors describe a prototype system for distribution of hypotheses and the accompanying rendering tasks to individual processors in a loosely-coupled computing environment, and demonstrate excellent performance improvements over a single-processor implementation. >

Abstract: We describe an accurate method of rendering by scan-conversion of closed regions bounded by NURBs, with particular comments on its application to computer-based 2D animation. It is shown that the method is fast, analytically accurate, and can be readily extended to include anti-aliasing and clipping.

Abstract: We present a new paradigm, called shell rendering, for volume visualization of surfaces. It significantly overcomes the two major impediments of current volume rendering methods -- high computational cost and storage requirements -- and makes interactive volume rendering feasible in a workstation environment via portable software. It imparts the notion of a structure -- a shell -- to what is usually treated as an amorphous semi-transparent volume and makes morphometrics of surfaces feasible in the volume rendering paradigm.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Abstract: UWGSP4 is configured with a parallel architecture for image processing and a pipelined architecture for computer graphics. The system's peak performance is 1,280 MFLOPS for image processing and over 200,000 Gouraud shaded 3-D polygons per second for graphics. The simulated sustained performance is about 50% of the peak performance in general image processing. Most of the 2-D image processing functions are efficiently vectorized and parallelized in UWGSP4. A performance of 770 MFLOPS in convolution and 440 MFLOPS in FFT is achieved. The real-time cine display, up to 32 frames of 1280 X 1024 pixels per second, is supported. In 3-D imaging, the update rate for the surface rendering is 10 frames of 20,000 polygons per second; the update rate for the volume rendering is 6 frames of 128 X 128 X 128 voxels per second. The system provides 1280 X 1024 X 32-bit double frame buffers and one 1280 X 1024 X 8-bit overlay buffer for supporting realistic animation, 24-bit true color, and text annotation. A 1280 X 1024- pixel, 66-Hz noninterlaced display screen with 1:1 aspect ratio can be windowed into the frame buffer for the display of any portion of the processed image or graphics.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Abstract: The Eurographics hardware workshops have become an established forum for the exchange of information about the latest developments in computer graphics hardware, a field of growing importance. This volume contains papers representing a comprehensive record of the contributions to the fifth workshop at EG '90 in Lausanne. The first part is devoted to rendering machines. The papers in this part address techniques for accelerating the rendering of images and efficient ways of improving their quality. The second part, on ray tracing, describes algorithms and architectures for producing photorealistic images, with emphasis on ways of reducing the time needed for this computationally intensive task. The third part, on visualization systems, covers a number of topics, including voxel-based systems, radiosity, animation and special rendering techniques. The contributions show there is flourishing activity in the development of new algorithmic and architectural ideas and in absorbing the impact of VLSI technology. The increasing diversity of applications encourages new solutions, and graphics hardware has become a research area of high activity and importance.

Abstract: Graphics rendering architecture suffers from at least three major performance bottlenecks which limit the interactive display of 3D photorealistic graphics databases. The performance bottlenecks are graphics database traversal, the pixel computation rate of a single graphics oriented processor and the frame buffer access rate of a conventional frame buffer. The authors look at solutions for increasing the pixel computation rate. Pixel computation rate is directly related to the design of the geometry and rasterization architectures of the graphics rendering system. The goal is to design geometry and rasterization hardware and software that accelerates the floating point processing requirements of object space algorithms and pixel processing requirements of image space algorithms. >

Abstract: Computer graphics is receiving much attention in the development of interactive educational software, multimedia systems, and many other applications. It not only adds a new dimension to such applications but also makes them more exciting and dynamic. Furthermore, the use of computer graphics is already well accepted in computer science education. If skillfully and relevantly used, it can be an important component of computer-assisted instruction, which is an educational application area with tremendous potential.

Abstract: The authors examine the various hardware methodologies used to accelerate image rendering. An architecture capable of being implemented on a VLSI chip to effectively carry out this objective is presented. The architecture uses inherent parallelism in the rendering algorithm and processes multiple scan lines simultaneously. The architecture is scalable with multiple copies of the chip and a set up processor being used to enhance output. Use of memory interlacing and banks avoids the possibility of memory bandwidth posing a bottleneck. The Gouraud shading algorithm was chosen for implementation. The simulation of the architecture is discussed. >

Abstract: This paper attempts to share all information obtained in researching the graphics inclusion in LATEX, from using the picture environment to using EPS graphics, briefly discussing how graphics enter user documents, the graphics packages available to accomplish graphics inclusion, and the various uses of the \special command for the SSCL printers.

Abstract: Part 1: personal view, structure of book system - overview of system winsom - geometry and algorithms for "what I can see", lighting and rendering, texture, tay-tracer interactive graphics - picture style and hardware, interactive graphics software, view manipulation, interaction animation - preview, final ESME and graphics programming - high level language, function image output - screen hard copy. Part 2 Art specific: art overview form design mutator animation conclusion.

Abstract: Visual, intelligent and personal communications computer vision and model-based coding virtual reality simulated nature volume rendering isosurfaces rendering computer-aided geometric design interpolation and fitting sweep methods hidden surfaces and hidden curve algorithms Raster technologies rules-and constraints-based coding animation dynamic and kinematic modelling tools and environment.