We describe an image based rendering approach that generalizes many image based rendering algorithms currently in use including light field rendering and view-dependent texture mapping. In particular it allows for lumigraph style rendering from a set of input cameras that are not restricted to a plane or to any specific manifold. In the case of regular and planar input camera positions, our algorithm reduces to a typical lumigraph approach. In the case of fewer cameras and good approximate geometry, our algorithm behaves like view-dependent texture mapping. Our algorithm achieves this flexibility because it is designed to meet a set of desirable goals that we describe. We demonstrate this flexibility with a variety of examples. Keyword Image-Based Rendering 1

In image-based rendering, images acquired from a scene are used to represent the scene itself. A number of reference images are required to fully represent even the simplest scene. This leads to a number of problems during image acquisition and subsequent reconstruction. We present the multiple-center-of-projection image, a single image acquired from multiple locations, which solves many of the problems of working with multiple range images. This work develops and discusses multiple-center-ofprojection images, and explains their advantages over conventional range images for image-based rendering. The contributions include greater flexibility during image acquisition and improved image reconstruction due to greater connectivity information. We discuss the acquisition and rendering of multiple-center-of-projection datasets, and the associated sampling issues. We also discuss the unique epipolar and correspondence properties of this class of image. CR Categories: I.3.3 [Computer Graphic...

Many disciplines must handle the creation, visualization, and manipulation of huge and complex 3D environments. Examples include large structural and mechanical engineering projects dealing with entire cars, ships, buildings, and processing plants. The complexity of such models is usually far beyond the interactive rendering capabilities of todays 3D graphics hardware. Previous approaches relied on costly preprocessing for reducing the number of polygons that need to be rendered per frame but suffered from excessive precomputation times --- often several days or even weeks.

The images generated by real-time 3D graphics systems exhibit enormous frame-to-frame coherence, which is not exploited by the conventional graphics pipeline. I exploit this coherence by decoupling image rendering from image display. My system renders every Nth frame in the conventional manner, and generates the in-between frames with an image warper. The image warper modifies a rendered image so that it is approximately correct for a new viewpoint and view direction. My image warper uses McMillan's 3D image warp. Unlike perspective image warps, the 3D image warp can correct for changes in viewpoint, even for objects at different depths. As a result, my system does not require the application programmer to segment the scene into different depth layers, as is required by systems that use a perspective image warp. I attack thr...

We present a new data structure for encoding the appearance of a geometric model as seen from a viewing region (view cell). This representation can be used in interactive or real-time visualization applications to replace a complex model by an impostor, maintaining high quality rendering while cutting down rendering time. Our approach relies on an object-space sampled representation similar to a point cloud or a layered depth image, but introduces two fundamental additions to previous techniques. First, the sampling rate is controlled to provide sufficient density across all possible viewing conditions from the specified view cell. Second, a correct, antialiased representation of the plenoptic function is computed using Monte Carlo integration. Our system therefore achieves high quality rendering using a simple representation with bounded complexity. We demonstrate the method for an application in urban visualization.

Abstract not found

Over the last six years, the automatic simplification of polygonal models has become an important tool for achieving interactive frame rates in the visualization of complex virtual environments. Initial methods employed clever heuristics, but no real quality metrics; then measures of quality for these simplified output models began to develop. This dissertation focuses on the use of error metrics to provide guaranteed error bounds for the simplifications we create. We guarantee bounds on the total appearance of our simplifications with respect to the three major appearance attributes: surface position, surface curvature (normal), and material color. We present the simplification envelopes and successive mappings algorithms for geometric simplification, two unique approaches that bound the maximum surface-to-surface deviation between the input surface and the simplif...

In this paper, we propose a triangle-based view interpolation algorithm which can correctly resolve the visibility problem without depth-buffering. The algorithm is especially useful when depth information is not available, such as in the case of real-world photographs. By subdividing the reference image into variable-sized triangles, view interpolation can be done efficiently using existing graphics hardware. We derive the drawing order between each pair of neighboring triangles from the epipolar geometry. Using this drawing order, a graph can be built and topological sorting is applied on the graph to obtain the complete drawing order of all triangles in linear time. 1

Ray tracing is a straightforward and powerful image synthesis technique but usually requires many rays per pixel to eliminate the aliasing or noise in the nal image. However, not all the pixels in the image require the same quantity of rays. In this paper we introduce new measures for supersampling re nement criteria, based on colour and geometry. These measures use the entropy, one of the most relevant Information Theory concepts. All the new measures are compared with other classic contrast measures.

In this paper we present a general technique for real-time display of very large models. We combine methods for culling and level-ofdetail management with wire-frame representations, generated dynamically from a hierarchy of bounding volumes. Smoothly moving boundary planes ensure that changes of representation do not lead to distracting popping effects. Context-sensitive landmark objects are added to support navigation, with a minimal impact on display frame rates. The method uses four dynamically-managed, overlapping zones to control level of detail. Results from user evaluation experiments are presented to demonstrate that the technique is effective for very large models on a modestly priced PC. 1 Introduction This paper describes a technique for real-time display of massive models. Although illustrated with respect to one particular application -- process plant walk-through -- the method is general, although its effectiveness will depend on the type of application. Process plants ...