Abstract: Modern graphics hardware architectures excel at compute-intensive tasks such as ray-triangle intersection, making them attractive target platforms for raytracing. To date, most GPU-based raytracers have relied upon uniform grid acceleration structures. In contrast, the kd-tree has gained widespread use in CPU-based raytracers and is regarded as the best general-purpose acceleration structure. We demonstrate two kd-tree traversal algorithms suitable for GPU implementation and integrate them into a streaming raytracer. We show that for scenes with many objects at different scales, our kd-tree algorithms are up to 8 times faster than a uniform grid. In addition, we identify load balancing and input data recirculation as two fundamental sources of inefficiency when raytracing on current graphics hardware.

Abstract: In this work we present a flexible framework for GPU-based volume rendering. The framework is based on a single pass volume raycasting approach and is easily extensible in terms of new shader functionality. We demonstrate the flexibility of our system by means of a number of high-quality standard and non-standard volume rendering techniques. Our implementation shows a promising performance in a number of benchmarks while producing images of higher accuracy than obtained by standard pre-integrated slice-based volume rendering.

Abstract: We present a modified photon mapping algorithm capable of running entirely on GPUs. Our implementation uses breadth-first photon tracing to distribute photons using the GPU. The photons are stored in a grid-based photon map that is constructed directly on the graphics hardware using one of two methods: the first method is a multipass technique that uses fragment programs to directly sort the photons into a compact grid. The second method uses a single rendering pass combining a vertex program and the stencil buffer to route photons to their respective grid cells, producing an approximate photon map. We also present an efficient method for locating the nearest photons in the grid, which makes it possible to compute an estimate of the radiance at any surface location in the scene. Finally, we describe a breadth-first stochastic ray tracer that uses the photon map to simulate full global illumination directly on the graphics hardware. Our implementation demonstrates that current graphics hardware is capable of fully simulating global illumination with progressive, interactive feedback to the user.

Abstract: Extensively updated to reflect the evolution of statistics and computing, the second edition of the bestselling R Graphics comes complete with with new packages and new examples Paul Murrell, widely known as the leading expert on R graphics, has developed an in-depth resource that helps both neophyte and seasoned users master the intricacies of R graphics New in the Second Edition Updated information on the core graphics engine, the traditional graphics system, the grid graphics system, and the lattice package A new chapter on the ggplot2 package New chapters on applications and extensions of R Graphics, including geographic maps, dynamic and interactive graphics, and node-and-edge graphs Organized into five parts, R Graphics covers both "traditional" and newer, R-specific graphics systems The book reviews the graphics facilities of the R language and describes Rs powerful grid graphics system The book then covers the graphics engine, which represents a common set of fundamental graphics facilities, and provides a series of brief overviews of some of the major areas of application for R graphics, and some of the major extensions of R graphics

Abstract: Volume visualization is a method of extracting meaningful information from volumetric data using interactive graphics and imaging. It is concerned with volume data representation, modeling, manipulation, and rendering. Volume data are 3D (possibly time-varying) entities that may have information inside them, may not consist of tangible surfaces and edges, or may be too voluminous to be represented geometrically. They are obtained by sampling, simulation, or modeling techniques. When volumetric data are visualized using a surface-rendering technique, a dimension of information is essentially lost. In response to this, volume rendering techniques were developed that attempt to capture the entire 3D data in a single 2D image. Volume rendering conveys more information than surface-rendered images but at the cost of increased algorithm complexity and consequently increased rendering times. To improve interactivity in volume rendering, many optimization methods both for software and graphics-accelerator implementations as well as several special-purpose volume rendering machines have been developed.

Abstract: Harvesting the power of modern graphics hardware to solve the complex problem of real-time rendering of large unstructured meshes is a major research goal in the volume visualization community. While, for regular grids, texture-based techniques are well-suited for current GPUs, the steps necessary for rendering unstructured meshes are not so easily mapped to current hardware. We propose a novel volume rendering technique that simplifies the CPU-based processing and shifts much of the sorting burden to the GPU, where it can be performed more efficiently. Our hardware-assisted visibility sorting algorithm is a hybrid technique that operates in both object-space and image-space. In object-space, the algorithm performs a partial sort of the 3D primitives in preparation for rasterization. The goal of the partial sort is to create a list of primitives that generate fragments in nearly sorted order. In image-space, the fragment stream is incrementally sorted using a fixed-depth sorting network. In our algorithm, the object-space work is performed by the CPU and the fragment-level sorting is done completely on the GPU. A prototype implementation of the algorithm demonstrates that the fragment-level sorting achieves rendering rates of between one and six million tetrahedral cells per second on an ATI Radeon 9800.

Abstract: A 36 mm/sup 2/ graphics processor with fixed-point programmable vertex shader is designed and implemented for portable two-dimensional (2-D) and three-dimensional (3-D) graphics applications. The graphics processor contains an ARM-10 compatible 32-bit RISC processor,a 128-bit programmable fixed-point single-instruction-multiple-data (SIMD)vertex shader, a low-power rendering engine, and a programmable frequency synthesizer (PFS). Different from conventional graphics hardware, the proposed graphics processor implements ARM-10 co-processor architecture with dual operations so that user-programmable vertex shading is possible for advanced graphics algorithms and various streaming multimedia processing in mobile applications. The circuits and architecture of the graphics processor are optimized for fixed-point operations and achieve the low power consumption with help of instruction-level power management of the vertex shader and pixel-level clock gating of the rendering engine. The PFS with a fully balanced voltage-controlled oscillator (VCO) controls the clock frequency from 8 MHz to 271 MHz continuously and adaptively for low-power modes by software. The chip shows 50 Mvertices/s and 200 Mtexels/s peak graphics performance, dissipating 155 mW in 0.18-/spl mu/m 6-metal standard CMOS logic process.

Abstract: The invention provides methods for leveraging data in the graphics pipeline of a 3D graphics application for use in a haptic rendering of a virtual environment. The invention provides methods for repurposing graphical information for haptic rendering. Thus, at least part of the work that would have been performed by a haptic rendering process to provide touch feedback to a user is obviated by work performed by the graphical rendering process.

Abstract: We propose an adaptive form of frameless rendering with the potential to dramatically increase rendering speed over conventional interactive rendering approaches. Without the rigid sampling patterns of framed renderers, sampling and reconstruction can adapt with very fine granularity to spatio-temporal color change. A sampler uses closed-loop feedback to guide sampling toward edges or motion in the image. Temporally deep buffers store all the samples created over a short time interval for use in reconstruction and as sampler feedback. GPU-based reconstruction responds both to sampling density and space-time color gradients. Where the displayed scene is static, spatial color change dominates and older samples are given significant weight in reconstruction, resulting in sharper and eventually antialiased images. Where the scene is dynamic, more recent samples are emphasized, resulting in less sharp but more up-to-date images. We also use sample reprojection to improve reconstruction and guide sampling toward occlusion edges, undersampled regions, and specular highlights. In simulation our frameless renderer requires an order of magnitude fewer samples than traditional rendering of similar visual quality (as measured by RMS error), while introducing overhead amounting to 15% of computation time.

Abstract: Implementations of transforms, such as a discrete cosine transform (DCT) and inverse DCT on a graphics processing unit (GPU), use direct matrix multiplication. GPU features such as parallel graphics pipelines, multi-channel capability, and multiple render targets are used to obtain significantly faster processing speeds than on a conventional central processing unit (CPU). Various rendering modes may be used, such as point rendering mode, line rendering mode, and triangle or quadrilateral rendering mode.

Abstract: Modern graphics architectures have replaced stages of the graphics pipeline with fully programmable modules. Therefore, it is now possible to perform fairly general computation on each vertex or fragment in a scene. In addition, the nature of the graphics pipeline makes substantial computational power available if the programs have a suitable structure. In this paper, we show that it is possible to cleanly map a state-of-the-art tone mapping algorithm to the pixel processor. This allows an interactive application to achieve higher levels of realism by rendering with physically based, unclamped lighting values and high dynamic range texture maps. We also show that the tone mapping operator can easily be extended to include a time-dependent model, which is crucial for interactive behavior. Finally, we describe the ways in which the graphics hardware limits our ability to compress dynamic range efficiently, and discuss modifications to the algorithm that could alleviate these problems.

Abstract: Iso-surface construction and rendering on programmable graphics hardware has recently been shown for tetrahedral grids. In this paper, we present a novel edge-based approach that avoids redundant computations of edge‐surface intersections. We show how to achieve a significant performance gain by considering intrinsic features of recent GPUs. The iso-surface extraction process is re-formulated in a way that reduces both numerical computations and memory access operations. A span-space data structure allows us to avoid the processing of elements not intersected by the selected surface. Finally, to allow for the rendering of transparent surfaces, a GPU sorting routine is integrated into the rendering pass. Our applications show numerical simulation results, distance volumes and advanced shading effects.

Abstract: The raw compute performance of today's graphics processor is truly amazing. With peak performance of over 60 GFLOPS, the compute power of today's graphics processor (GPU) dwarfs that of the commodity CPU at a price of only a few hundred dollars. As the programmability and performance of modern graphics hardware continues to increase, many researchers are looking to graphics hardware to solve computationally intensive problems previously performed on general purpose CPUs. The challenge, however, is how to re-target these processors from game rendering to general computation, such as numerical modeling, scientific computing, or signal processing. Traditional graphics APIs abstract the GPU as a rendering device, involving textures, triangles, and pixels. Mapping an algorithm to use these primitives is not a straightforward operation, even for the most advanced graphics developers. In this dissertation, we explore the concept of stream computing with GPUs. We describe the stream processor abstraction and how this abstraction and corresponding programming model can efficiently represent computation on the GPU. To formalize the model, we present Brook for GPUs, a programming system for general-purpose computation on programmable graphics hardware. Brook extends C to include simple data-parallel constructs, enabling the use of the GPU as a streaming co-processor. We present a compiler and runtime system that abstracts and virtualizes many aspects of graphics hardware. In addition, we present an analysis of the effectiveness of the GPU as a streaming processor and evaluate the performance of a collection of benchmark applications in comparison to their CPU implementations. For a variety of the applications explored in this dissertation, we demonstrate that our Brook implementations performs up to seven times faster than their CPU counterparts. We also discuss some of the algorithmic decisions which are critical for efficient execution when using the stream programming model for the GPU.

Abstract: Mobile devices have evolved to a point where interactive 3D graphics is becoming feasible. The first standardized 3D programming interfaces for mobile devices - OpenGL ES for native C/C++ and Mobile 3D Graphics (M3G) for Java applications - are now available to hardware vendors and application developers. The interfaces complement rather than compete with each other and can share the same underlying rendering engine, whether implemented in hardware or software. Three-dimensional graphics on mobile devices is still about converting descriptions of geometry, material, and illumination into pixels shown on a raster display, using the same fundamental algorithms as elsewhere. However, mobile devices' limited capabilities must be reflected in the realizations of those algorithms, as well as in the overall graphics system design. In this article, we describe a design that attempts to take on that challenge, consisting of OpenGL ES, a low-level API, and M3G (also known as JSR-184), a high-level API for Java. We describe how the two interfaces relate to each other and existing graphics architectures on the desktop, and how they attempt to provide optimal features and performance across the whole gamut of different devices. OpenGL ES and M3G, as well as our presentation of them in this article, derive from a long tradition of graphics systems design.

Abstract: With the tremendous advances in both hardware capabilities and rendering algorithms, rendering performance is steadily increasing. Even consumer graphics hardware can render many million triangles per second. However, scene complexity seems to be rising even faster than rendering performance, with no end to even more complex models in sight.In this paper, we are targeting the interactive visualization of the "Boeing 777" model, a highly complex model of 350 million individual triangles, which - due to its sheer size and complex internal structure - simply cannot be handled satisfactorily by today's techniques. To render this model, we use a combination of real-time ray tracing, a low-level out of core caching and demand loading strategy, and a hierarchical, hybrid volumetric/lightfield-like approximation scheme for representing not-yet-loaded geometry. With this approach, we are able to render the full 777 model at several frames per second even on a single commodity desktop PC.

Abstract: Existing parallel or remote rendering solutions rely on communicating pixels, OpenGL commands, scene-graph changes or application-specific data. We propose an intermediate solution based on a set of independent graphics primitives that use hardware shaders to specify their visual appearance. Compared to an OpenGL based approach, it reduces the complexity of the model by eliminating most fixed function parameters while giving access to the latest functionalities of graphics cards. It also suppresses the OpenGL state machine that creates data dependencies making primitive re-scheduling difficult. Using a retained-mode communication protocol transmitting changes between each frame, combined with the possibility to use shaders to implement interactive data processing operations instead of sending final colors and geometry, we are able to optimize the network load. High level information such as bounding volumes is used to setup advanced schemes where primitives are issued in parallel, routed according to their visibility, merged and re-ordered when received for rendering. Different optimization algorithms can be efficiently implemented, saving network bandwidth or reducing texture switches for instance. We present performance results based on two VTK applications, a parallel iso-surface extraction and a parallel volume renderer. We compare our approach with Chromium. Results show that our approach leads to significantly better performance and scalability, while offering easy access to hardware accelerated rendering algorithms.

Abstract: Models of large forest scenes are of a geometric complexity that surpasses even the capabilities of current high end graphics hardware. We propose an extreme simplification method which allows us to render such scenes in realtime. Our work is an extension of the image based-simplification method of Billboard Clouds. We automatically generate tree model representations of 15-50 textured polygons. In this paper, we focus on the algorithmic details to improve the simplification process for foliage. We use the simplified models as static levels-of-detail in the medium to far field and demonstrate how our approach yields real-time rendering of dense forest scenes for walkthroughs and flyovers.

Abstract: Author(s): Lefohn, Aaron; Sengupta, Shubhabrata; Kniss, Joe M.; Strzodka, Robert; Owens, John D. | Abstract: We present a novel implementation of adaptive shadow maps (ASMs) that performs all shadow lookups and scene analysis on the GPU, enabling interactive rendering with ASMs while moving both the light and camera. Adaptive shadow maps offer a rigorous solution to projective and perspective shadow map aliasing while maintaining the simplicity of a purely image-based technique. The complexity of the ASM data structure, however, has prevented full GPU-based implementations until now. Our approach uses an entirely GPU-based data structure and a blend of graphics and GPU stream programming. We support shadow map effective resolutions up to 131,072 x 131,072 and, unlike previous implementations, provide smooth transitions between resolution levels by trilinearly filtering (mipmapping) the shadow lookups.

Abstract: During the quick advancements of medical image visualization and augmented virtual reality application, the low performance of the volume rendering algorithm is still a "bottle neck". To facilitate the usage of well developed hardware resource, a novel graphics processing unit (GPU)-based volume ray-casting algorithm is proposed in this paper. Running on a normal PC, it performs an interactive rate while keeping the same image quality as the traditional volume rendering algorithm does. Recently, GPU-accelerated direct volume rendering has positioned itself as an efficient tool for the display and visual analysis of volume data. However, for large sized medical image data, it often shows low efficiency for too large memories requested. Furthermore, it always holds a drawback of writing color buffers multi-times per frame. The proposed algorithm improves the situation by implementing ray casting operation completely in GPU. It needs only one slice plane from CPU and one 3Dtexture to store data when GPU calculates the two terminals of the ray and carries out the color blending operation in its pixel programs. So both the rendering speed and the memories consumed are improved, and the algorithm can deal most medical image data on normal PCs in the interactive speed

Abstract: We present a vertex compression technique suitable for efficient decompression on graphics hardware. Given a user-specified number of bits per vertex, we automatically allocate bits to vertex attributes for quantization to maximize quality, guided by an image-space error metric. This allocation accounts for the constraints of graphics hardware by packing the quantized attributes into bins associated with the hardware's vectorized vertex data elements. We show that this general approach is also applicable if the user specifies a total desired model size. We present an algorithm that integrally combines vertex decimation and attribute quantization to produce the best quality model for a user-specified data size. Such models have an appropriate balance between the number of vertices and the number of bits per vertex.Vertex data is transmitted to and optionally stored in video memory in the compressed form. The vertices are decompressed on-the-fly using a vertex program at rendering time. Our algorithms not only work well within the constraints of current graphics hardware but also generalize to a setting where these constraints are relaxed. They apply to models with a wide variety of vertex attributes, providing new tools for optimizing space and bandwidth constraints of interactive graphics applications.

Abstract: We present a method of fully dynamically rendered virtual humans with variety in color, animation and appearance. This is achieved by using vertex and fragment shaders programmed in the OpenGL shading language (GLSL). We then compare our results with a fixed function pipeline based approach. We also show a color variety creation GUI using HSB color space restriction. An improved version of the LOD pipeline for our virtual characters is presented. With these new techniques, we are able to use a full dynamic animation range in the crowd populating the Aphrodisias odeon (which is part of the ERATO project), i.e., a greater repertoire of animations, smooth transitions and more variety and speed. We show how a multi-view of the rendering data can ensure good batching of rendering primitives and comfortable constant time access.

Abstract: Real-time rendering of photo-realistic humans is considerably outside the scope of current consumer-level computer hardware. There are many techniques, which attempt to bridge the gap between what is desired and what is possible. This paper aims to give an overview of the techniques designed to alter the complexity of the model's geometry (level of detail), or replace it with a flat image (visual impostor) and to improve the lighting model (lighting and shadows). Recent years have shown a boom in the power and availability of consumer-level programmable graphics processors, thus techniques that make use of these features are coming to the forefront.

Abstract: A system for displaying graphical information. The system includes an asset server for storing information and a rendering server in communication with the asset server. The rendering server receives a graphics command and renders graphic display data in response to the graphics command and to the information. The rendering server is independently addressable from the asset server.

Abstract: A computer automated process is presented for accelerating the rendering of sparse volume data on Graphics Processing Units (GPUs). GPUs are typically SIMD processors, and thus well suited to processing continuous data and not sparse data. The invention allows GPUs to process sparse data efficiently through the use of scatter-gather textures. The invention can be used to accelerate the rendering of sparse volume data in medical imaging or other fields.

Abstract: We identify a general paradigm for portal-based rendering and present an image-space algorithm for rendering complex portals. Our general paradigm is an abstraction of portal-based rendering that is independent of scene geometry. It provides a framework for flexible and dynamic scene composition by connecting cells with transformative portals. Our rendering algorithm maintains a visible volume in image-space and uses fragment culling to discard fragments outside of this volume. We discuss our implementation in OpenGL and present results that show it provides correct rendering of complex portals at interactive rates on current hardware. We believe that our work is useful in many applications that require a means of creating dynamic and meaningful visual connections between different sets of data.