GPU-based raycasting is the state-of-the-art rendering technique for interactive volume visualization. The ray traversal is usually implemented in a fragment shader, utilizing the hardware in a way that was not originally intended. New programming interfaces for stream processing, such as CUDA, support a more general programming model and the use of additional device features, which are not accessible through traditional shader programming. In this paper we propose a slab-based raycasting technique that is modeled specifically to use these features to accelerate volume rendering. This technique is based on experience gained from comparing fragment shader implementations of basic raycasting to implementations directly translated to CUDA kernels. The comparison covers direct volume rendering with a variety of optional features, e.g., gradient and lighting calculations. Our findings are supported by benchmarks of typical volume visualization scenarios. We conclude that new stream processing models can only gain a small performance advantage when directly porting the basic raycasting algorithm. However, they can be advantageous through novel acceleration methods which use the hardware features not available to shader implementations.

Modern High-Performance Ray Casting toolkits, such as the Intel Embree library, which is a de facto industry standard, are a cornerstone of the high- performance levels seen in current CPU rendering. The purpose of Embree is an easy integration into professional image synthesis environments to ac- celerate rendering scenes with complex geometry, usually composed of many primitives. Unfortunately, Embree does not offer support for rendering con- structive solid geometry (CSG), solids composed of a manageable amount of primitive solids by using set operations. This is a significant drawback since CSG modeling is an intuitive and powerful option for describing com- plex geometry. In this thesis, we describe the integration of Embree into the predictive rendering system ART and propose a method for rendering CSG by combining the traversal of Embree's and ART's internal ray acceler- ation data structures. The tests we conducted with virtual scenes containing CSG not being constructed from triangle meshes showed that our method is competitive with the original ART renderer and often even faster. 1

A modality device can today capture high resolution volumetric data sets and as the data resolutions increase so does the challenges of processing volumetric data through a visualization pipeline. Standard volume rendering pipelines often use a graphic processing unit (GPU) to accelerate rendering performance by taking beneficial use of the parallel architecture on such devices. Unfortunately, graphics cards have limited amounts of video memory (VRAM), causing a bottleneck in a standard pipeline. Multi-resolution techniques can be used to efficiently modify the rendering pipeline, allowing a sub-domain within the volume to be represented at different resolutions. The active resolution distribution is temporarily stored on the VRAM for rendering and the inactive parts are stored on secondary memory layers such as the system RAM or on disk. The active resolution set can be optimized to produce high quality renders while minimizing the amount of storage required. This is done by using a dynamic compression scheme which optimize the visual quality by evaluating user-input data. The optimized resolution of each sub-domain is then, on demand, streamed to the VRAM from secondary memory layers. Rendering a multi-resolution data set requires some extra care between boundaries of sub-domains. To avoid artifacts, an intrablock interpolation (II) sampling scheme capable of creating smooth transitions between sub-domains at arbitrary resolutions can be used. The result is a highly optimized rendering pipeline complemented with a preprocessing pipeline together capable of rendering large volumetric data sets in real-time.

Direct Volume Rendering (DVR) is a technique for creating images directly from a representation of a function defined over a three-dimensional domain. The technique has many application fields, such as scientific visualization and medical imaging. A striking property of the data sets produced within these fields is their ever increasing size and complexity. Despite the advancements of computing resources these data sets seem to grow at even faster rates causing severe bottlenecks in terms of data transfer bandwidths, memory capacity and processing requirements in the rendering pipeline. This thesis focuses on efficient methods for DVR of large data sets. At the core of the work lies a level-of-detail scheme that reduces the amount of data to process and handle, while optimizing the level-of-detail selection so that high visual quality is maintained. A set of techniques for domain knowledge encoding which significantly improves assessment and prediction of visual significance for blocks in a volume are introduced. A complete pipeline for DVR is presented that uses the data reduction achieved by the level-of-detail selection to minimize the data requirements in all stages. This leads to reduction of disk I/O as well as host and graphics memory. The data reduction is also exploited to improve the rendering performance in graphics hardware, employing adaptive sampling both within the volume and within the rendered image. The developed techniques have been applied in particular to medical visualization of large data sets on commodity desktop computers using consumer graphics processors. The specific application of virtual autopsies has received much interest, and several developed data classification schemes and rendering techniques have been motivated by this application. The results are, however, general and applicable in many fields and significant performance and quality improvements over previous techniques are shown. / On the defence date the status of article IX was Accepted.

Volume rendering is quite an old concept of representing images, dating back to the 1980's. It is very useful in the medical field for visualizing the results of a computer tomography (CT) and magnet resonance tomography (MRT) in 3D. Apart from these two major applications for volume rendering, there aren’t many other fields of usage accept from tech demos. Volumetric data does not have any limitations to the shape of an object that ordinary meshes can have. A popular way of representing volume data is through an algorithm that is called volume raycasting. There is a big disadvantage with this algorithm, namely that it is computationally heavy for the hardware. However, there have been vast improvements of the graphic cards (GPUs) in recent years and with the first GPU implementation of volume raycasting in 2003, how does this algorithm perform on modern hardware? Can the performance of the algorithm be improved with the introduction of GPGPU (DirectCompute) in Directx 11? The performance results of the basic version and the DirectCompute version was compared in this thesis and revealed significant improvement in performance. Speedup was indeed possible when using DirectCompute to optimize volume raycasting. / Implementation, optimering och prestandamätning av en volume rendering algoritm som heter volume raycasting. Optimeringen är utförd med hjälp av DirectCompute i Directx 11.

This thesis deals with design and implementation of an application for medical data imaging in real-time. The first part of project is focused on methods for obtaining data in medical practice and visualization of large volume data on computer using familiar rendering approaches. Similar applications are used outside of medicine in other fields, such as chemistry to display molecular structures or microorganisms. Another part of project will focus on benefits of visualization of volumetric data using programmable hardware and new methods of parallelization of algorithms on graphics card using CUDA technology, and OpenCL. The resulting application will display the volume of medical data based on selected method accelerated by programmable shaders, and time-consuming operations will be paralleled on graphics card.