Humans perceive the three-dimensional structure of the world with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem and what is the current state of the art? Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos. More than just a source of recipes, this exceptionally authoritative and comprehensive textbook/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting them to produce descriptions of a scene. These problems are also analyzed using statistical models and solved using rigorous engineering techniques Topics and features: structured to support active curricula and project-oriented courses, with tips in the Introduction for using the book in a variety of customized courses; presents exercises at the end of each chapter with a heavy emphasis on testing algorithms and containing numerous suggestions for small mid-term projects; provides additional material and more detailed mathematical topics in the Appendices, which cover linear algebra, numerical techniques, and Bayesian estimation theory; suggests additional reading at the end of each chapter, including the latest research in each sub-field, in addition to a full Bibliography at the end of the book; supplies supplementary course material for students at the associated website, http://szeliski.org/Book/. Suitable for an upper-level undergraduate or graduate-level course in computer science or engineering, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries. Its design and exposition also make it eminently suitable as a unique reference to the fundamental techniques and current research literature in computer vision.

/pdf/computer-vision-algorithms-and-applications-25dn6wu83j.pdf

Computer Vision: Algorithms and Applications

A morphable model for the synthesis of 3D faces

The rapid increase in the performance of graphics hardware, coupled with recent improvements in its programmability, have made graphics hardware a compelling platform for computationally demanding tasks in a wide variety of application domains. In this report, we describe, summarize, and analyze the latest research in mapping general-purpose computation to graphics hardware. We begin with the technical motivations that underlie general-purpose computation on graphics processors (GPGPU) and describe the hardware and software developments that have led to the recent interest in this field. We then aim the main body of this report at two separate audiences. First, we describe the techniques used in mapping general-purpose computation to graphics hardware. We believe these techniques will be generally useful for researchers who plan to develop the next generation of GPGPU algorithms and techniques. Second, we survey and categorize the latest developments in general-purpose application development on graphics hardware. This survey should be of particular interest to researchers who are interested in using the latest GPGPU applications in their systems of interest.

/pdf/a-survey-of-general-purpose-computation-on-graphics-hardware-2phx1q9xxr.pdf

A Survey of General-Purpose Computation on Graphics Hardware

A Survey of General-Purpose Computation on Graphics Hardware.

The ability to interactively control viewpoint while watching a video is an exciting application of image-based rendering. The goal of our work is to render dynamic scenes with interactive viewpoint control using a relatively small number of video cameras. In this paper, we show how high-quality video-based rendering of dynamic scenes can be accomplished using multiple synchronized video streams combined with novel image-based modeling and rendering algorithms. Once these video streams have been processed, we can synthesize any intermediate view between cameras at any time, with the potential for space-time manipulation.In our approach, we first use a novel color segmentation-based stereo algorithm to generate high-quality photoconsistent correspondences across all camera views. Mattes for areas near depth discontinuities are then automatically extracted to reduce artifacts during view synthesis. Finally, a novel temporal two-layer compressed representation that handles matting is developed for rendering at interactive rates.

/pdf/high-quality-video-view-interpolation-using-a-layered-495xiwkbeh.pdf

High-quality video view interpolation using a layered representation

Objective Modern neuronavigation systems lack spatial accuracy during ongoing surgical procedures because of increasing brain deformation, known as brain shift. Intraoperative magnetic resonance imaging was used for quantitative analysis and visualization of this phenomenon. Methods For a total of 64 patients, we used a 0.2-T, open-configuration, magnetic resonance imaging scanner, located in an operating theater, for pre- and intraoperative imaging. The three-dimensional imaging data were aligned using rigid registration methods. The maximal displacements of the brain surface, deep tumor margin, and midline structures were measured. Brain shift was observed in two-dimensional image planes using split-screen or overlay techniques, and three-dimensional, color-coded, deformable surface-based data were computed. In selected cases, intraoperative images were transferred to the neuronavigation system to compensate for the effects of brain shift. Results The results demonstrated that there was great variability in brain shift, ranging up to 24 mm for cortical displacement and exceeding 3 mm for the deep tumor margin in 66% of all cases. Brain shift was influenced by tissue characteristics, intraoperative patient positioning, opening of the ventricular system, craniotomy size, and resected volume. Intraoperative neuronavigation updating (n = 14) compensated for brain shift, resulting in reliable navigation with high accuracy. Conclusion Without brain shift compensation, neuronavigation systems cannot be trusted at critical steps of the surgical procedure, e.g., identification of the deep tumor margin. Intraoperative imaging allows not only evaluation of and compensation for brain shift but also assessment of the quality of mathematical models that attempt to describe and compensate for brain shift.

Quantification of, visualization of, and compensation for brain shift using intraoperative magnetic resonance imaging.

Interactive direct volume rendering has yet been restricted to high-end graphics workstations and special-purpose hardware, due to the large amount of trilinear interpolations, that are necessary to obtain high image quality. Implementations that use the 2D-texture capabilities of standard PC hardware, usually render object-aligned slices in order to substitute trilinear by bilinear interpolation. However the resulting images often contain visual artifacts caused by the lack of spatial interpolation. In this paper we propose new rendering techniques that significantly improve both performance and image quality of the 2D-texture based approach. We will show how in ulti-texturing capabilitiesof modern consumer PC graphboards are exploited to enable in teractive high quality volume visualization on low-cost hardware. Furthermore we demonstrate how multi-stage rasterization hardware can be used to efficiently render shaded isosurfaces and to compute diffuse illumination for semi-transparent volume rendering at interactive frame rates.

https://www.cg.informatik.uni-siegen.de/data/Publications/2000/rezk_Publ.2000.5.pdf

Interactive volume on standard PC graphics hardware using multi-textures and multi-stage rasterization

Clipping 2D polygons is one of the basic routines in computer graphics. In rendering complex 3D images it has to be done several thousand times. Efficient algorithms are therefore very important. We present such an efficient algorithm for clipping arbitrary 2D-polygons. The algorithm can handle arbitrary closed polygons, specifically where the clip and subject polygons may self-intersect. The algoirthm is simple and faster that Vatti's (1992) algorithm, which was designed for the general case as well. Simple modifications allow determination of union and set-theoretic differences of two arbitrary polygons.

/pdf/efficient-clipping-of-arbitrary-polygons-5d5e93snod.pdf

Efficient clipping of arbitrary polygons

https://www.cg.informatik.uni-siegen.de/publicationPDFbyID?ID=22

Strategies for brain shift evaluation.

We present a simple algorithm for computing a high-quality personalized avatar from a single color image and the corresponding depth map which have been captured by Microsoft's Kinect sensor. Due to the low market price of our hardware setup, 3D face scanning becomes feasible for home use. The proposed algorithm combines the advantages of robust non-rigid registration and fitting of a morphable face model. We obtain a high-quality reconstruction of the facial geometry and texture along with one-to-one correspondences with our generic face model. This representation allows for a wide range of further applications such as facial animation or manipulation. Our algorithm has proven to be very robust. Since it does not require any user interaction, even non-expert users can easily create their own personalized avatars. Copyright © 2011 John Wiley & Sons, Ltd.

/pdf/automatic-reconstruction-of-personalized-avatars-from-3d-agqt3lyg05.pdf

Günther Greiner

Papers

Quantification of, visualization of, and compensation for brain shift using intraoperative magnetic resonance imaging.

Interactive volume on standard PC graphics hardware using multi-textures and multi-stage rasterization

Efficient clipping of arbitrary polygons

Strategies for brain shift evaluation.

Automatic reconstruction of personalized avatars from 3D face scans