Abstract: Using parallel processing for visualization speeds up computer graphics rendering of complex data sets. A parallel algorithm designed for polygon scan conversion and rendering is presented which supports fast rendering of highly complex data sets using advanced lighting models. Dedicated graphics rendering engines do not necessarily suit such data sets, although they can support real-time update of moderately complex scenes using simple lighting. Advantages to using a software-based approach include the feasibility of adding special rendering features to the program and the capability of integrating a parallel scientific application with a parallel graphics renderer. A new work decomposition strategy presented, called task adaptive, is based on dynamically partitioning the amount of computational work left at a given time. The algorithm uses a heuristic for dynamic task decomposition in which image space tasks are partitioned without requiring interruption of the partitioned processor. A sophisticated memory referencing strategy lets local memory access graphics data during rendering. This permits implementation of the algorithm on a distributed memory multiprocessor. An in-depth analysis of the overhead costs accompanying parallel processing shows where performance is adequate or could be improved. >

Abstract: A rendering device for providing 3-D graphics rendering in a computer system. A hardware scanline rendering approach is utilized. Using a hardware scanline rendering approach the bandwidth requirements between a system frame buffer and the rendering device are minimized. The minimization of bandwidth requirement allows for the rendering device to be used with existing computer system designs while keeping design changes at a minimum. The result is that for a given desired performance of a combined computer system and rendering device, the cost of both the computer system without the rendering device, and the cost of the rendering device itself may be reduced. The rendering device is generally comprised of a bus attachment for coupling to the system bus of the computer system; a scanline rendering device and a scanout device for transferring the scanline of shaded pixel values to the system frame buffer.

Abstract: We describe the architecture of a hardware accelerator for volume rendering. The system basically consists of four VLSI chips and the volume memory and represents a singleboard solution to the computational challenges of volume visualization. It generates arbitrary perspective projections, so that walk-through examinations are possible. The classification of structures of interest is an integral part of the rendering pipeline. Image quality is enhanced by providing Phong shading, depth-cueing and support for translucency. Despite its compactness and algorithmic complexity, the system is able to render 2563 data sets at a sustained frame generation rate of about 2.5Hz. CR

Abstract: We present two new techniques for rendering 3D vector fields in scientific visualisation. We also present a new technique called texture splats for rendering these volumes efficiently. >

Abstract: One of the drawbacks of standard volume rendering techniques is that is it often difficult to comprehend the three-dimensional structure of the volume from a single frame; this is especially true in cases where there is no solid surface. Generally, several frames must be generated and viewed sequentially, using motion parallax to relay depth. Another option is to generate a single spectroscopic pair, resulting in clear and unambiguous depth information in both static and moving images. Methods have been developed which take advantage of the coherence between the two halves of a stereo pair for polygon rendering and ray-tracing, generating the second half of the pair in significantly less time than that required to completely render a single image. This paper reports the results of implementing these techniques with parallel ray-traced volume rendering. In tests with different data types, the time savings is in the range of 70--80%.

Abstract: Applications which run on parallel supercomputers are often characterized by massive datasets. Converting these vast collections of numbers to visual form has proven to be a powerful aid to comprehension. For a variety of reasons, it may be described to provide this visual feedback at runtime. One way to accomplish this is to exploit the available parallelism to perform graphics operations in place. In order to do this, we need appropriate parallel rendering algorithms and library interfaces. This paper provides a tutorial introduction to some of the issues which arise in designing parallel graphics libraries and their underlying rendering algorithms. The focus is on polygon rendering for distributed memory message-passing systems. We illustrate our discussion with examples from PGL, a parallel graphics library which has been developed on the Intel family of parallel systems.

Abstract: Spray rendering provides a framework for creating and experimenting with different visualization techniques. The name spray rendering is derived from the metaphor of using a virtual spray can to paint data sets. Varying the type of paint in the can highlights data in different ways. Spray rendering is not limited to the paint metaphor, however. Other useful metaphors include a flashlight and a probe. Thus, spray rendering refers to the localized nature of the visualization algorithms and the manner in which the algorithms are sent to the data sets. We gain several advantages by looking at visualization algorithms in this way, including extensibility, grid independence, and ability to handle large data sets. This article presents the benefits, conceptual design, issues and directions of spray rendering. >

Abstract: introductory computer graphics course. They represent a wide spectrum of the discipline, offering courses emphasizing systems, engineering, mathematics, science, art design and animation. Sample course syllabi, textbook recommendations, software packages and suggested projects will be available. This past summer at an Undergraduate Faculty Enhancement Workshop in Computer Graphics sponsored by the NSF and the ACM SIGGRAPH Education Committee, it became apparent that there were widely different viewpoints on the content and methodology for teaching the introductory computer graphics course. The panelists will discuss various approaches to teaching an introductory computer graphics course. They represent a wide spectrum of the discipline, offering courses emphasizing in systems, engineering, mathematics, science, art design and animation. Included in the discussion will be conventional approaches, beginning with two-dimensional concepts and introducing three-dimensional concepts at the end of the course; an approach that focus on generic graphics pipeline elements and system specification/implementation; a new approach that emphasizes image synthesis based on Physics; and approaches that emphasize art design and animation. Software packages, both commercial and public domain, used to teach computer graphics will be described. The courses described are taught at large public universities as well as small private colleges. The equipment used varies from 8088 personal computers to Sun workstations. Sample course syllabi, textbook recommendations, and suggested projects will be available.

Abstract: The simulation of global illumination has become a major focus in computer graphics, as physically based and accurate computation techniques are developed. We review some of the most recent advances, such as incremental radiosity computations for changing environments, and the simulation of arbitrary reflectance distributions. A discussion of persistent problems in physically-based illumination simulation follows, with an emphasis on the design issues faced by application developers. 1 Possible applications for physically accurate simulations In recent years, many new applications of sophisticated computer graphics have emerged, as new algorithms became available to perform physically meaningful simulations. Early computer graphics algorithms treated light and illumination as a necessary but otherwise ~nimportant step, as they focused on hidden surface elimination, or surface representation Issues. With the introduction of the radiosity method in 1984 [GTGB84)' the problem of computing illumination in a scene began to be viewed as the simulation of a physical problem: that of light transfer and energy balance. Radiosity methods have quickly attracted a lot of attention, and have matured surprisingly quickly, to become a reference for high-quality rendering. Why is radiosity needed? or more generally, why is a faithful simulation of the physical behavior of light needed ? These questions were frequently asked a few years ago, when the most remarkable feature of radiosity programs was their running time. The introduction of radiosity occured at a time when robust and simple shading algorithms were being implemented in hardware, and when "high quality rendering" was defined as ray tracing with shadows and specular reflections. In contrast, the early radiosity algorithms were slow, not very robust in that they produced visible artifacts, and limited to diffuse reflectors. Their usefulness was therefore questionable. In this context, the primary effect of these early developments on the field of computer graphics has been to trigger a growing awareness of the need for accuracy in rendering. Aside from the entertainment applications, most of the professional users of computer graphics actually need some kind of realism in their pictures : Industrial design tasks are an obvious example, where designers want to experiment with very well defined lighting cases, and to obtain reproducible and meaningful images. In the auto industry, for example, special light sources are used to reveal any discontinuities in the shape of the surfaces, and they have to be modeled accurately. Some applications explicitly require quantitative accuracy, such as lighting design, when norms have to be met by the simulated light distribution. In architectural design applications, the simulation must also be in quantitative agreement with reality, if decisions are to be based on the resulting images. More generally, studies in human perception show that some visual cues are very important to help understand synthetic pictures, and that shadows constitute a very important aid in the comprehension of a 3D environment from a 2D picture [Wan91]. Similarly, global illumination effects can be expected to help in the understanding of an image.

Abstract: The RenderMan interface has been proposed as a general interface to rendering systems, yet only a few implementations of the interface exist In this paper we describe the implementation of the RenderMan interface on a general rendering architecture that supports various rendering algorithms Specifically we discuss the implementation of the RenderMan Shading Language and its integration into our rendering architecture Special attention is focused on the problems that we have encountered and how they can be solved Additionally, we suggest extensions and enhancements to the current interface definition, which would make RenderMan easier to implement and more flexible to use

Abstract: A scheme for the visualization of large data volumes using volume rendering on a distributed memory MIMD system is described. The data to be rendered is decomposed into subvolumes to reside in the local memories of the system's nodes. A partial image of the local data is generated at each node by ray tracing, and is then composited with partial images on other nodes in the correct order to generate the complete Image. Subvolumes whose voxels are classified as being mapped to zero opacity are not rendered, giving rise to an imbalance of work amongst nodes. Scattered decomposition is used for load balancing, which on one hand: creates additional overheads in compositing and communication, but on the other, provides an improvement in throughput that is dependent on the characteristics of the data. Experimental results for a typical data set rendered on a 1024-node Fujitsu AP1000 are reported. >

Abstract: We describe the operational principles of a scalable hardware accelerator for volume rendering. The basic philosophy is to provide an atomic unit which already provides sophisticated volume graphics at interactive rendering speed. Realtime speed can then be achieved by operating multiple units in parallel. The basic unit consists of just four VLSI chips and the volume memory and thus meets the requirements of a small size and low costs. Nevertheless it provides arbitrary perspective projections (e.g., for walk-throughs), Phong shading, a freely moveable light source, depth-cueing and interactive, non-binary classification (semitransparent display) at a frame rate of about 2.5Hz for 2563 data sets.

Abstract: At the most abstract level, data visualization maps discrete values computed over an n-dimensional domain onto pixel colors. It is largely a dimension-reducing process justified by its leverage on human perceptual capacities for extracting information from visual stimuli. The difficulty is to implement a mapping that reveals the data characteristics relevant to the application at hand. Effective visualization solutions let the user control the process parameters interactively and enhance the automatically extracted features. We argue for an intelligent, model-based approach to visualization, which extracts the intrinsic data characteristics and constructs multiresolution graphics models suitable for interactive rendering on commercially available hardware adapters. The model-based approach has four parts, which we summarize. >

Abstract: The graphics applications of a 2-D graphics computer system provide each object to be rendered on a 2-D raster display with a pair of rendering reference coordinates (x and y), and a relative depth value (z). Additionally, the computer system is provided with a library of predetermined 2-D images and sounds, and a number of graphics toolkit routines. As the user "moves", the graphics toolkit routines render selected ones of the predetermined images based on x/z and y/z values of recomputed x and y rendering coordinates and the relative depth value z of the objects, and actuate the sounds if applicable based on their predetermined manners of rendering. As a result, the objects that are further away from the user will move slower than the objects that are closer to the user, thereby introducing the effect of parallax and added realism to the 2-D graphics computer system at a substantially lower cost.

Abstract: Multiple color objects are optimally rendered in a single print job, such that, for example, the rendering of presentation graphics images may be carried out differently than the rendering of sampled images, by use of remapped graphics paint operators and a plurality of color rendering dictionaries that operate in the interpretation of a page description in a computer-based publishing system.

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: 3-D rendering, dynamic exploration, and friendlier environments are among the newest trends in the field of data visualisation. The author discusses these trends. A table is given which lists data analysis and visualisation software packages. A brief description of each package is given. >

Abstract: Using Pixel-Planes 5, a parallel multicomputer for computer graphics [Fuchs 90], wehave constructed a system for visualizing volumetric medical data based on polygonalapproaches to surface rendering. The goal is a medical visualization system that hasintuitive navigation and exploration capabilities to present 3D clinical data using threedimensional images. To provide a natural navigation of patient data, segmentationparameters should provide user feedback at minimum rates of one update per second,and viewing direction and lighting control should respond in tenths of seconds. Ourapproach differs from other methods under investigation at UNC [Yoo 92] as we takeadvantage of the hardware graphics accelerators for polygon rendering rather thanattempt direct volume rendering.

Abstract: This paper describes a system for modeling, animating, previewing and rendering articulated objects. The system has a modeler of objects that consists of joints and segments. The animator interactively positions the articulated object in its stick, control vertex, or rectangular prism representation and previews the motion in real time. Then the data representing the motion and the models is sent to a multicomputer [iPSC/2 Hypercube (Intel)]. The frames are rendered in parallel, exploiting the coherence between successive frames, thus cutting down the rendering time significantly. Our main aim is to make a detailed study on rendering of a sequence of 3D scenes. The results show that due to an inherent correlation between the 3D scenes, an efficient rendering can be achieved.

Abstract: This chapter describes the graphics and visualization in computer system. The field of computer graphics encompasses many areas of synthetic image generation and representation. Applications of computer graphics range from modern user interface libraries to three-dimensional modeling and rendering. As more computer performance is made available, the ability to make use of high performance has enhanced the techniques used and images created by computer graphics systems. Most image processing and rendering techniques are used to project three-dimensional objects onto a two-dimensional surface. There are basically three ways to incorporate illumination into a graphics image: (1) the empirical model, (2) the transitional model, and (3) the analytical model. The basic idea behind the ray tracing algorithm is to consider all possible light sources and how they physically interact with each object in the object space. The Reality Engine is a specialized graphics system designed for rendering lighted, smooth-shaded, and texture-mapped objects. The Reality Engine is built as a collection of FIFO queues, command processor, geometry engines, fragment generators, and image engines.

Abstract: Introduction to Windows Programming Working with Display Devices Drawing Lines and Curves Filled Figures Working with Colours Working with Bitmaps Text and Fonts Presentation Graphics Animation Fractal Landscapes Two-Dimensional Graphics Techniques Interactive Drawing Tools An Object-Oriented Drawing Program Introduction to Three-Dimensional Graphics A Wire-Frame Viewer Rendering Solid Objects Multimedia and Video.

Abstract: practitioner in computer graphics was a solid background in geometry, algebra, calculus, topology, probability, mechanics, electromagnetism, signal processing, image processing, electrical engineering, mechanical engineering, optics, information theory, structured programming, basic algorithms and data structures, complexity theory, computer architecture, human factors, perceptual psychology, colorimetry, graphic design, industrial design, semiotics, and art! Unfortunately, the list is growing, and one more topic can now be included: optimization. A perusal of the computer-graphics literature reveals a recent trend towards using optimization to solve problems in image rendering, object modeling, animation, and even chart graphics. The techniques used run the gamut from standard function-optimization algorithms that have their roots in continuous mathematics [10], to black-art stochastic techniques that are inspired by natural processes like evolution and annealing [2]. The participants in the panel reflect this diversity in problem domain and optimization approach. Each panelist will list problems in his areas of expertise for which optimization techniques have proven effective, describe the optimization methods that have been most successful for these problems, present a representative example from the panelist’s own research of an optimization problem and method, attempt to predict the future impact of optimization on computer graphics, and suggest how engineers and artists might apply optimization techniques to practical problems.

Abstract: We present a parallel system for fast rendering of artificial scenes with photo realism. The underlying parallel algorithm is based on ray-tracing and radiosity shading. The system consists of a standard workstation, a medium-size mesh of cluster processors and a high-bandwidth interconnection between them. Each cluster processor consists of a programmable TMS320C40 core and three dedicated VLSI satellites. The rendering algorithm runs on both the workstation host and its rendering mate in a true shared/distributed manner. The system is the result of an exercise in combined algorithm and architecture design as well as software/hardware co-design.

Abstract: A distributed graphics programming language called DGLa is presented, which facilitates the development of distributed graphics application. Facilities for distributed programming and graphics support are included in it. It not only supports synchronous and asynchronous communication but also provides programmer with multiple control mechanism for process communication. The graphics support of DGLa is powerful, for both sequential graphics library and parallel graphics library are provided. The design consideration and implementation experience are discussed in detail in this paper. Application example are also given.

Abstract: The objective of the ESPRIT Project 6173 Design by Simulation and Rendering on Parallel Architectures (DESIRE) is to develop and demonstrate key software components of a system for interactive design of complex industrial products or parts thereof by simulation and rendering on parallel architectures. The software components communicate using a unified format for the exchange of data and control information. They will be demonstrated in the context of a prototype system for interactive design and engineering of car bodies based on visual feedback through photorealistic rendering and through visualization of simulated external air flow. This feedback is essential for both aesthetic and physical design decisions. In this paper we primarily address the requirements for the rendering software component and outline our solution to meet these. Some preliminary results concerning the implementation are reported. To put the development into perspective, we also present an overview of the structure of the prototype interactive system to be developed in the project and of the general exchange format that is used for communication between the components of the system.

Abstract: The graphics applications of a 2-D graphics computer system provide each object to be rendered on a 2-D raster display with a pair of rendering reference coordinates (x and y), and a relative depth value (z). Additionally, the computer system is provided with a library of predetermined 2-D images and sounds, and a number of graphics toolkit routines. As the user "moves", the graphics toolkit routines render selected ones of the predetermined images based on x/z and y/z values of recomputed x and y rendering coordinates and the relative depth value z of the objects, and actuate the sounds if applicable based on their predetermined manners of rendering. As a result, the objects that are further away from the user will move slower than the objects that are closer to the user, thereby introducing the effect of parallax and added realism to the 2-D graphics computer system at a substantially lower cost.

Abstract: It is often desirable to draw a detailed and realistic representation of surface data on a computer graphics display. One such representation is a 3D shaded surface. Conventional techniques for rendering shaded surfaces are slow, however, and require substantial computational power. Furthermore, many techniques suffer from aliasing effects, which appear as jagged lines and edges. This paper describes an algorithm for the fast rendering of shaded surfaces without aliasing effects. It is much faster than conventional ray tracing and polygon-based rendering techniques and is suitable for interactive use. On an IBM RISC System/6000TM workstation it renders a 1000 X 1000 surface in about 7 seconds.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.