Image-based Rendering

We advocate the use of point sets to represent shapes. We provide a definition of a smooth manifold surface from a set of points close to the original surface. The definition is based on local maps from differential geometry, which are approximated by the method of moving least squares (MLS). The computation of points on the surface is local, which results in an out-of-core technique that can handle any point set. We show that the approximation error is bounded and present tools to increase or decrease the density of the points, thus allowing an adjustment of the spacing among the points to control the error. To display the point set surface, we introduce a novel point rendering technique. The idea is to evaluate the local maps according to the image resolution. This results in high quality shading effects and smooth silhouettes at interactive frame rates.

Image based rendering using undersampled light fields suffers from aliasing effects. These effects can be drastically reduced by using some geometric information. In pop-up light field rendering [18], the scene is segmented into coherent layers, usually corresponding to approximately planar regions, that can be rendered free of aliasing. As opposed to the supervised method in the pop-up light field, we propose an unsupervised extraction of coherent regions. The problem is posed in a multidimensional variational framework using the level set method [16]. Since the segmentation is done jointly over all the images, coherence can be imposed throughout the data. However, instead of using active hypersurfaces, we derive a semi-parametric methodology that takes into account the constraints imposed by the camera setup and the occlusion ordering. The resulting framework is a global multidimensional region competition that is consistent in all the images and efficiently handles occlusions. We show the validity of the method with some captured multi-view datasets. Other special effects by coherent region manipulation are also demonstrated.

This paper gives an overview of computer graphics representations of trees commonly used for the rendering of complex scene of vegetation. Looking for the right compromise between realism and efficiency has lead researchers to consider various types of geometrical plant models with different types of complexity. To achieve realist plant model, a complex structure of plant with full details is generally considered. In contrast, to promote efficiency, other approaches summarize plant geometry with few primitives allowing rapid rendering. Finally, to find a good compromise, structures with adaptive complexity are defined. Theses different types of representations and the ways to use them are presented, classified and discussed. The proposed classification principles rely on the type of structural details used in the plants representations. Characterization of all these methods is completed with various additional criteria including rendering primitive type, distance validity, interacti...

. Synthesized images (top) of a CT head data set, created using proxy images (bottom). (a) Using multi-perspective proxy images, we can visualize multiple layers of a 3D object (shown in (b)) in multiple orientations. We can also inexpensively simulate complex lighting models such as proxy-based ambient occlusion, while retaining the spatial relationships between semi-transparent layers. This is done without accessing volume data. (c) Accumulated attenuation proxy images allow us to explore data sets in transfer function space and to apply depth-aware enhancement, which highlights shape and alleviates depth ambiguities, often found in static images. (d) We can combine accumulated attenuation proxy images (shown in (c)) with depth proxy images (below) to support lighting effects. (g) Multi-perspective accumulated attenuation proxy images allow us to visualize a volumetric object in multiple orientations.

This paper presents a new hybrid Kinect-variety based synthesis scheme that renders artifacts-free multiple views for autostereoscopic/ auto-multiscopic displays. The proposed approach does not explicitly require dense scene depth information for synthesizing novel views from arbitrary viewpoints. Instead, the integrated framework first constructs a consistent minimal image-space parameterization of the underlying 3D scene. The compact representation of scene structure is formed using only implicit sparse depth information of few reference scene points extracted from raw RGB-D data. The views from arbitrary positions can be inferred by moving the novel camera in parameterized space by enforcing Euclidean constraints on reference scene images under a full-perspective projection model. Unlike state-of-the-art DIBR methods, where input depth map accuracy is crucial for high quality output, our proposed algorithm does not depend on precise per-pixel geometry information. Therefore, it simply sidesteps to recover and refine the incomplete or noisy depth estimates with advanced filling or upscaling techniques. Our approach performs fairly well in unconstrained indoor/outdoor environments, where the performance of range sensors or dense depth-based algorithms could be seriously affected due to scene complex geometric conditions. We demonstrate that the proposed hybrid scheme provides guarantees on the completeness, optimality with respect to the inter-view consistency of the algorithm. In the experimental validation, we performed a quantitative evaluation as well as subjective assessment on scene with complex geometric or surface properties. Comparison with latest representative DIBR methods is additionally performed to demonstrate the superior performance of the proposed scheme.

The purpose of this project was to create several methods for achieving non-photorealistic appearance of the objects or, in other words, the goal was to create several different implementations of the cartoonish shader, which can sometimes be referred to as a cel-shader or just toon-shader.

Technological advances and challenges ] M ultiview imaging (MVI) has attracted considerable attention recently due to its increasingly wide range of applications and the decreasing cost of digital cameras. This opens up many new and interesting research topics and applications, such as virtual view synthesis for three-dimensional (3-D) television (3DTV) and entertainment, high-performance imaging, video processing and analysis for surveillance, distance learning, industry inspection, etc.

Este documento es un ejercicio elaborado durante el seminario de área impartido por el Dr. Peter Krieger en la Maestría en Arquitectura de la UNAM, en donde se abordan temas de interés actual que son parte de la producción arquitectónica y de ciudad así como los modos de difusión de ellas, como lo son las imágenes virtuales, y las consecuencias tangibles que tiene esta difusión sobre la ciudad, explicado a partir de un centro comercial en proceso de construcción como caso de estudio, siendo una tipología de edificación que ha tomado fuerza en Ciudad de México y en otras del mundo.

This paper presents real-time reconstruction of dynamic 3D avatar for interactive mixed reality. In computer graphics, one of the main goals is the combination of virtual scenes with real-world scenes. However, the views of the real world objects are often restricted to views from the cameras. True navigation through such mixed reality scenes becomes impossible unless the components from real objects can be rendered from arbitrary viewpoints. Additionally, adding a real-world object to a virtual scene requires some depth information as well, in order to handle interaction. The proposed algorithm introduces an approach to generate 3D video avatars and to augment the avatars naturally into 3D virtual environment using the calibrated camera parameters and silhouette information. As a result, we can create photo-realistic live avatars from natural scenes and the resulting 3D live avatar can guide and interact participants in VR space.

This paper presents a novel solution for approximations to some large convolution kernels by leveraging a weighted box-filtered image pyramid set. Convolution filters are widely used, but still compute-intensive for real-time rendering when the kernel size is large. Our algorithm approximates the convolution kernels, such as Gaussian and cosine filters, by two phases of down and up sampling on a GPU. The computational complexity only depends on the input image resolution and is independent of the kernel size. Therefore, our method can be applied to nonuniform blurs, irradiance probe generations, and ray-traced glossy global illuminations in real time, and runs in effective and efficient performance.

Automatic attendance system is one of the significant issues of today's research. Among other methods, human face recognition is highly used technique for attendance automation. Many systems have been proposed in literature using face recognition. Most of the systems are using fixed camera and desktop computers. We propose a system using mobile phones where an image is captured of group of peoples and face detection is done automatically. While considering computational and storage power of mobile devices, extracted local binary features for detected faces are then transferred to server machine using firebase database. Matching is done on server side, if face recognized than attendance is marked and feedback is sent back to client side. Experiments show effectiveness of proposed techniques with 95% correct recognition rate.

This paper presents a novel approach to creating full view panoramic mosaics from image sequences. Unlike current panoramic stitching methods, which usually require pure horizontal camera panning, our system does not require any controlled motions or constraints on how the images are taken (as long as there is no strong motion parallax). For example, images taken from a hand-held digital camera can be stitched seamlessly into panoramic mosaics. Because we represent our image mosaics using a set of transforms, there are no singularity problems such as those existing at the top and bottom of cylindrical or spherical maps. Our algorithm is fast and robust because it directly recovers 3D rotations instead of general 8 parameter planar perspective transforms. Methods to recover camera focal length are also presented. We also present an algorithm for efficiently extracting environment maps from our image mosaics. By mapping the mosaic onto an artibrary texture-mapped polyhedron surrounding the origin, we can explore the virtual environment using standard 3D graphics viewers and hardware without requiring special-purpose players.

In this paper, we survey the techniques for image-based rendering (IBR) and for compressing image-based representations. Unlike traditional three-dimensional (3-D) computer graphics, in which 3-D geometry of the scene is known, IBR techniques render novel views directly from input images. IBR techniques can be classified into three categories according to how much geometric information is used: rendering without geometry, rendering with implicit geometry (i.e., correspondence), and rendering with explicit geometry (either with approximate or accurate geometry). We discuss the characteristics of these categories and their representative techniques.

We present an approach to convert a small portion of a light field with extracted depth information into a cinematic effect with simulated, smooth camera motion that exhibits a sense of 3D parallax. We develop a taxonomy of the cinematic conventions of these effects, distilled from observations of documentary film footage and organized by the number of subjects of interest in the scene. We present an automatic, content-aware approach to apply these cinematic conventions to an input light field. A face detector identifies subjects of interest. We then optimize for a camera path that conforms to a cinematic convention, maximizes apparent parallax, and avoids missing information in the input. We describe a GPUaccelerated, temporally coherent rendering algorithm that allows users to create more complex camera moves interactively, while experimenting with effects such as focal length, depth of field, and selective, depth-based desaturation or brightening. We evaluate and demonstrate our approach on a wide variety of scenes and present a user study that compares our 3D cinematic effects to their 2D counterparts.

In this paper, we survey the techniques for image-based rendering. Unlike traditional 3D computer graphics in which 3D geometry of the scene is known, image-based rendering techniques render novel views directly from input images. Previous image-based rendering techniques can be classified into three categories according to how much geometric information is used: rendering without geometry, rendering with implicit geometry (i.e., correspondence), and rendering with explicit geometry (either with approximate or accurate geometry). We discuss the characteristics of these categories and their representative methods. The continuum between images and geometry used in image-based rendering techniques suggests that image-based rendering with traditional 3D graphics can be united in a joint image and geometry space.

We present a novel technique for texture synthesis using optimization. We define a Markov Random Field (MRF)-based similarity metric for measuring the quality of synthesized texture with respect to a given input sample. This allows us to formulate the synthesis problem as minimization of an energy function, which is optimized using an Expectation Maximization (EM)-like algorithm. In contrast to most example-based techniques that do region-growing, ours is a joint optimization approach that progressively refines the entire texture. Additionally, our approach is ideally suited to allow for controllable synthesis of textures. Specifically, we demonstrate controllability by animating image textures using flow fields. We allow for general two-dimensional flow fields that may dynamically change over time. Applications of this technique include dynamic texturing of fluid animations and texture-based flow visualization.

Valuable 3D graphical models, such as high-resolution digital scans of cultural heritage objects, may require protection to prevent piracy or misuse, while still allowing for interactive display and manipulation by a widespread audience. We have investigated techniques for protecting 3D graphics content, and we have developed a remote rendering system suitable for sharing archives of 3D models while protecting the 3D geometry from unauthorized extraction. The system consists of a 3D viewer client that includes lowresolution versions of the 3D models, and a rendering server that renders and returns images of high-resolution models according to client requests. The server implements a number of defenses to guard against 3D reconstruction attacks, such as monitoring and limiting request streams, and slightly perturbing and distorting the rendered images. We consider several possible types of reconstruction attacks on such a rendering server, and we examine how these attacks can be defended against without excessively compromising the interactive experience for non-malicious users.

Using coarse meshes with textures and/or normal maps to represent detailed meshes often results in poor visual quality along silhouettes. To tackle this problem, we introduce silhouette texture, a new data structure for capturing and reconstructing the silhouettes of detailed meshes. In addition to the recording of color and normal fields in traditional methods, we sample information that represents the original silhouettes and pack it into a three dimensional texture. In the rendering stage, our algorithm extracts relevant information from the texture to rebuild the silhouettes for any perspective view. Unlike previous work, our approach is based on GPU and could achieve high rendering performance. Moreover, both exterior and interior silhouettes are processed for better approximation quality. In addition to rendering acceleration, our algorithm also enables detailed silhouette visualization with minimum geometric complexity.

This paper presents a novel 3D plenoptic function, which we call concentric mosaics. We constrain camera motion to planar concentric circles, and create concentric mosaics using a manifold mosaic for each circle (i.e., composing slit images taken at different locations). Concentric mosaics index all input image rays naturally in 3 parameters: radius, rotation angle and vertical elevation. Novel views are rendered by combining the appropriate captured rays in an efficient manner at rendering time. Although vertical distortions exist in the rendered images, they can be alleviated by depth correction. Like panoramas, concentric mosaics do not require recovering geometric and photometric scene models. Moreover, concentric mosaics provide a much richer user experience by allowing the user to move freely in a circular region and observe significant parallax and lighting changes. Compared with a Lightfield or Lumigraph, concentric mosaics have much smaller file size because only a 3D plenoptic function is constructed. Concentric mosaics have good space and computational efficiency, and are very easy to capture. This paper discusses a complete working system from capturing, construction, compression, to rendering of concentric mosaics from synthetic and real environments.

Interactive visualization of architecture provides a way to quickly visualize existing or novel buildings and structures. Such applications require both fast rendering and an effortless input regimen for creating and changing architecture using high-level editing operations that automatically fill in the necessary details. Procedural modeling and synthesis is a powerful paradigm that yields high data amplification and can be coupled with fast-rendering techniques to quickly generate plausible details of a scene without much or any user interaction. Previously, forward generating procedural methods have been proposed where a procedure is explicitly created to generate particular content. In this paper, we present our work in inverse procedural modeling of buildings and describe how to use an extracted repertoire of building grammars to facilitate the visualization and quick modification of architectural structures and buildings. We demonstrate an interactive application where the user draws simple building blocks and, using our system, can automatically complete the building "in the style of" other buildings using view-dependent texture mapping or nonphotorealistic rendering techniques. Our system supports an arbitrary number of building grammars created from user subdivided building models and captured photographs. Using only edit, copy, and paste metaphors, the entire building styles can be altered and transferred from one building to another in a few operations, enhancing the ability to modify an existing architectural structure or to visualize a novel building in the style of the others.

In this paper we present a sketch modelling system which we call Stilton. The program resembles a desktop VRML browser, allowing a user to navigate a 3D model in a perspective projection, or panoramic photographs, which the program maps onto the scene as a 'floor' and 'walls'. We place an imaginary 2D drawing plane in front of the user, and any geometric information that user sketches onto this plane may be reconstructed to form solid objects through an optimisation process. We show how the system can be used to reconstruct geometry from panoramic images, or to add new objects to an existing model. While panoramic imaging can greatly assist with some aspects of site familiarisation and qualitative assessment of a site, without the addition of some foreground geometry they offer only limited utility in a design context. Therefore, we suggest that the system may be of use in 'just-intime' CAD recovery of complex environments, such as shop floors, or construction sites, by recovering objects through sketched overlays, where other methods such as automatic line-retrieval may be impossible. The result of using the system in this manner is the 'sketching of space' -sketching out a volume around the userand once the geometry has been recovered, the designer is free to quickly sketch design ideas into the newly constructed context, or analyse the space around them. Although end-user trials have not, as yet, been undertaken we believe that this implementation may afford a user-interface that is both accessible and robust, and that the rapid growth of pen-computing devices will further stimulate activity in this area.

We present a system for rendering very complex 3D models at interactive rates. We select a subset of the model as preferred viewpoints and partition the space into virtual cells. Each cell contains near geometry, rendered using levels of detail and visibility culling, and far geometry, rendered as a textured depth mesh. Our system automatically balances the screen-space errors resulting from geometric simplification with those from textureddepth-mesh distortion. We describe our prefetching and data management schemes, both crucial for models significantly larger than available system memory. We have successfully used our system to accelerate walkthroughs of a 13 million triangle model of a large coal-fired power plant and of a 1.7 million triangle architectural model. We demonstrate the walkthrough of a 1.3 GB power plant model with a 140 MB cache footprint.

We present an image-based rendering system to viewpoint-navigate through space and time of complex real-world, dynamic scenes. Our approach accepts unsynchronized, uncalibrated multi-video footage as input. Inexpensive, consumer-grade camcorders suffice to acquire arbitrary scenes, e.g., in the outdoors, without elaborate recording setup procedures, allowing also for hand-held recordings. Instead of scene depth estimation, layer segmentation, or 3D reconstruction, our approach is based on dense image correspondences, treating view interpolation uniformly in space and time: spatial viewpoint navigation, slow motion, or freeze-and-rotate effects can all be created in the same way. Acquisition simplification, integration of moving cameras, generalization to difficult scenes, and space-time symmetric interpolation amount to a widely applicable Virtual Video Camera system.

Il lavoro proposto vuole ottimizzare una metodologia di documentazione dell’architettura che, a partire dalle fotografie panoramiche, si misura di volta in volta con gli strumenti e le tecnologie a disposizione per proporre una soluzione integrata, speditiva e low-cost di Virtual Architecture.
La tecnica sviluppata nasce in un contesto di ricerca più ampio che da anni studia la possibilità di usare le immagini panoramiche sferiche per il rilievo metrico dell’architettura (Fangi, 2007-2012). I dati a disposizione (panoramiche orientate), l’affidabilità raggiunta e metodi di Image-based Modeling (d’Annibale, 2009-2011) sono alla base della proposta di una tipo di ricostruzione 3D integrata ed estremamente flessibile: dal rilievo professionale del patrimonio culturale alla sua comunicazione nei musei virtuali.
La soluzione proposta si sviluppa tramite l’integrazione e implementazione di diverse tecniche (Fotogrammetria Sferica, Structure From Motion, Image-based Modeling) e si pone l’obiettivo di raggiungere alti livelli di precisione metrica del rilievo e resa fotorealistica dei modelli ricostruiti. L’intera procedura risulta essere accessibile grazie alla scelta di utilizzare strumenti low-cost e adattabile allo scopo finale.
Diversi sono i livelli di documentazione possibili all’interno dell’unico processo proposto: dalla navigazione virtuale di panorami sferici a complessi sistemi di simulazione e ricostruzione virtuale.
Tools VR permettono l’integrazione delle tecnologie e lo sviluppo di nuove soluzioni per la navigazione virtuale.
Affinate tecniche di Image-based Modeling permettono la costruzione di modelli con texture fotorealistiche ad alta risoluzione.
L’alta risoluzione delle fotografie panoramiche, lo sviluppo di tools per la creazione di affidabili algoritmi di orientamento dei panorami e restituzione fotogrammetrica garantiscono precisioni centimetriche e texture ad alta risoluzione.
Tecniche automatizzate sono oggetto di indagine, successiva implementazione ed integrazione tramite tool ad hoc che sfruttano tutte le potenzialità delle fotografie panoramiche.
Il workflow di lavoro permette diversi tipi di output che vanno dalla fedele restituzione di punti tramite fotogrammetria sferica a dense nuvole di punti ottenuti da restituzione automatizzata. I dati opportunamente trattati ed integrati possono fornire diversi livelli di analisi e ricostruzione virtuale che uniscono la precisione della fotogrammetria alla resa foto realistica delle superfici modellate.
E’ stata infine testata una nuova soluzione di navigazione virtuale che all’interno dello stesso ambiente propone la possibilità di interagire contemporaneamente con i panorami sferici ad alta risoluzione orientati nello spazio e con il modello 3D ricostruito.

In this paper we present a set of efficient image based rendering methods capable of rendering multiple frames per second on a PC. The first method warps Sprites with Depth representing smooth surfaces without the gaps found in other techniques. A second method for more general scenes performs warping from an intermediate representation called a Layered Depth Image (LDI). An LDI is a view of the scene from a single input camera view, but with multiple pixels along each line of sight. The size of the representation grows only linearly with the observed depth complexity in the scene. Moreover, because the LDI data are represented in a single image coordinate system, McMillan's warp ordering algorithm can be successfully adapted. As a result, pixels are drawn in the output image in back-to-front order. No z-buffer is required, so alphacompositing can be done efficiently without depth sorting. This makes splatting an efficient solution to the resampling problem.

Image-based rendering takes as input multiple images of an object and generates photorealistic images from novel viewpoints. This approach avoids explicitly modeling scenes by replacing the modeling phase with an object reconstruction phase. Reconstruction is achieved in two possible ways: recovering 3D point locations using multiview stereo techniques, or reasoning about consistency of each voxel in a discretized object volume space.

In this paper we present an algorithm that accelerates 3D texturebased volume rendering of large and sparse data sets. A hierarchical data structure (known as AMR tree) consisting of nested uniform grids is employed in order to efficiently encode regions of interest. The hierarchies resulting from this kind of space partitioning yield a good balance between the amount of volume to render and the number of texture bricks -a prerequisite for fast rendering.

We present an image-based approach to relighting photographs of tree canopies. Our goal is to minimize capture overhead; thus the only input required is a set of photographs of the tree taken at a single time of day, while allowing relighting at any other time. We first analyze lighting in a tree canopy both theoretically and using simulations. From this analysis, we observe that tree canopy lighting is similar to volumetric illumination. We assume a single-scattering volumetric lighting model for tree canopies, and diffuse leaf reflectance; we validate our assumptions with synthetic renderings. We create a volumetric representation of the tree from 10-12 images taken at a single time of day and use a single-scattering participating media lighting model. An analytical sun and sky illumination model provides consistent representation of lighting for the captured input and unknown target times. We relight the input image by applying a ratio of the target and input time lighting representations. We compute this representation efficiently by simultaneously coding transmittance from the sky and to the eye in spherical harmonics. We validate our method by relighting images of synthetic trees and comparing to path-traced solutions. We also present results for photographs, validating with time-lapse ground truth sequences.

We present an architecture for rendering multiple views efficiently on a cluster of GPUs. The original scene is sampled by virtual cameras which are used later to reconstruct the desired views. We show that this image-based approach can be very scalable and support rendering at interactive rates.

We present a method that using only an uncalibrated camera allows the capture of object geometry and appearance, and then at a later stage registration and AR overlay into a new scene. Using only image information first a coarse object geometry is obtained using structure-from-motion, then a dynamic, view dependent texture is estimated to account for the differences between the reprojected coarse model and the training images. In AR rendering, the object structure is interactively aligned in one frame by the user, object and scene structure is registered, and rendered in subsequent frames by a virtual scene camera, with parameters estimated from real-time visual tracking. Using the same viewing geometry for both object acquisition, registration, and rendering ensures consistency and minimizes errors.

The available technologies for the presentation of audiovisual scenes to large audiences show different degrees of maturity. While high quality physics based rendering of 3D scenes is found in many visual applications, the presentation of the accompanying audio content is based on much simpler technologies. Multi-channel cinema sound systems are only capable of delivering sound effects, but they do not faithfully reproduce an acoustic scene. New methods for acoustic rendering are required to provide physically correct recreation of audiovisual environments. A new technology for the reproduction of sound fields is based on Huygen's principle. It utilizes a large number (tens or hundreds) of loudspeakers to recreate a 3D sound field based on the physical description of the original acoustic environment. This paper describes different aspects of this technology, presents applications pursued by the European project CARROUSO and our own contributions to the project including the development of algorithms for loudspeaker and listening room compensation and real-time software implementation of a rendering software on a PC.

This paper addresses the problem of synthesizing novel views of a scene using images taken by an uncalibrated translating camera. We propose a method for synthesis of views corresponding to translational motion of the camera. Our scheme can handle occlusions and changes in visibility in the synthesized views. We give a characterisation of the viewpoints corresponding to which views can be synthesized. Experimental results have established the validity and effectiveness of the method. Our synthesis scheme can also be used to detect translational pan motion of the camera in a given video sequence. We have also presented experimental results to illustrate this feature of our scheme.

Integral photography (IP), which is one of the ideal 3-D photographic technologies, can be regarded as a method of capturing and displaying light rays passing through a plane. The NHK Science and Technical Research Laboratories have developed a real-time IP system using an HDTV camera and an optical fiber array. In this paper, the authors propose a method of synthesizing arbitrary views from IP images captured by the HDTV camera. This is a kind of image-based rendering system, founded on the 4-D data space representation of light rays. Experimental results show the potential to improve the quality of images rendered by computer graphics techniques.

When the shape of an object is known, its appearance is determined by the spatially-varying reflectance function defined on its surface. Image-based rendering methods that use geometry seek to estimate this function from image data. Most existing methods recover a unique angular reflectance function (e.g., BRDF) at each surface point and provide reflectance estimates with high spatial resolution. Their angular accuracy is limited by the number of available images, and as a result, most of these methods focus on capturing parametric or low-frequency angular reflectance effects, or allowing only one of lighting or viewpoint variation. We present an alternative approach that enables an increase in the angular accuracy of a spatially-varying reflectance function in exchange for a decrease in spatial resolution. By framing the problem as scattered-data interpolation in a mixed spatial and angular domain, reflectance information is shared across the surface, exploiting the high spatial resolution that images provide to fill the holes between sparsely observed view and lighting directions. Since the BRDF typically varies slowly from point to point over much of an object's surface, this method enables image-based rendering from a sparse set of images without assuming a parametric reflectance model. In fact, the method can even be applied in the limiting case of a single input image.

Extrusion, bevel, chamfer, and lathe tools are widely used in a large variety of computer graphics applications such as architectural designs and industrial prototyping of manufactured goods. However, such modeling is usually based on polygonal meshes which often require a considerable amount of graphics primitives. In this article, we present a new image-based approach for rendering extruded and revolved surfaces. We use only a single RGBA texture which stores a binary map (i.e. The profile curve), its Euclidean distance transform, and the two components of the unit gradient vector of the distance fields. All rendering algorithms are based on a ray-tracing procedure performed in texture space. The use of the distance fields allows culling of empty space and thus minimizes the number of ray-tracing steps. The extrusion and revolution mapping techniques produce very convincing models, and both are rendered at interactive frame rates.

High quality, physically accurate rendering at interactive rates has widespread application, but is a daunting task. We attempt to bridge the gap between high-quality offline and interactive rendering by using existing environment mapping hardware in combination with a novel Image Based Rendering (IBR) algorithm. The primary contribution lies in performing IBR in reflection space. This method can be applied to ordinary environment maps, but for more physically accurate rendering, we apply reflection space IBR to radiance environment maps. A radiance environment map pre-integrates a Bidirectional Reflection Distribution Function (BRDF) with a lighting environment. Using the reflection-space IBR algorithm on radiance environment maps allows interactive rendering of arbitrary objects with a large class of complex BRDFs in arbitrary lighting environments. The ultimate simplicity of the final algorithm suggests that it will be widely and immediately valuable given the ready availability of hardware assisted environment mapping.

We describe a new framework for efficiently computing and storing global illumination effects for complex, animated environments. The new framework allows the rapid generation of sequences representing any arbitrary path in a "view space" within an environment in which both the viewer and objects move. The global illumination is stored as time sequences of range-images at base locations that span the view space. We present algorithms for determining locations for these base images, and the time steps required to adequately capture the effects of object motion. We also present algorithms for computing the global illumination in the base images that exploit spatial and temporal coherence by considering direct and indirect illumination separately. We discuss an initial implementation using the new framework. Results and analysis of our implementation demonstrate the effectiveness of the individual phases of the approach; we conclude with an application of the complete framework to a complex environment that includes object motion.

This paper introduces a novel application of IBR technology for efficient rendering of high quality CG and live action stereoscopic sequences. Traditionally, IBR has been applied to render novel views using image and depth based representations of the plenoptic functions. In this work, we present a restricted form of IBR in which lower resolution images for the views to be generated at a very high resolution are assumed to be available. Specifically, the paper addresses the problem of synthesizing stereo IMAX(R) 1 3D motion picture images at a standard resolution of 4-6K. At such high resolutions, producing CG content is extremely time consuming and capturing live action requires bulky cameras. We propose a Hybrid Stereo Camera concept in which one view is rendered at the target high resolution but the other is rendered at a much lower resolution. Methods for synthesizing the second view sequence at the target resolution using image analysis and IBR techniques are the focus of this work. The high quality results from the techniques presented in this paper have been visually evaluated in the IMAX 3D large screen projection environment. The paper also highlights generalizations and extensions of the hybrid stereo camera concept.

The paper addresses the problem of "class-based" imagebased recognition and rendering with varying illumination. The rendering problem is defined as follows: given a single input image of an object, and a sample of images with varying illumination conditions of other objects of the same general class, re-render the input image to simulate new illumination conditions. The class-based recognition problem is similarly defined: given a single image of an object in a database of images of other objects, some of them are multiply sampled under varying illumination, identify (match) any novel image of that object under varying illumination with the single image of that object in the database.

Special relativistic visualization offers the possibility of experiencing the optical effects of traveling near the speed of light, including apparent geometric distortions as well as Doppler and searchlight effects. Early high-quality computer graphics images of relativistic scenes were created using offline, computationally expensive CPU-side 4D ray tracing. Alternate approaches such as image-based rendering and polygon-distortion methods are able to achieve interactivity, but exhibit inferior visual quality due to sampling artifacts. In this paper, we introduce a hybrid rendering technique based on polygon distortion and local ray tracing that facilitates interactive high-quality visualization of multiple objects moving at relativistic speeds in arbitrary directions. The method starts by calculating tight image-space footprints for the apparent triangles of the 3D scene objects. The final image is generated using a single image-space ray tracing step incorporating Doppler and searchlight effects. Our implementation uses GPU shader programming and hardware texture filtering to achieve high rendering speed.

In this paper we present an algorithm that accelerates 3D texturebased volume rendering of large and sparse data sets. A hierarchical data structure (known as AMR tree) consisting of nested uniform grids is employed in order to efficiently encode regions of interest. The hierarchies resulting from this kind of space partitioning yield a good balance between the amount of volume to render and the number of texture bricks -a prerequisite for fast rendering.

This paper demonstrates the use of High Dynamic Range (HDR) fisheye images of the sky dome in lighting simulations. The objective is to improve the accuracy of simulations with site specific sky conditions. The luminance information stored at a pixel level in an ...