Search

Tracking the head in a video stream is a common thread seen within computer vision literature, supplying the research community with a large number of challenging and interesting problems. Head pose estimation from monocular cameras is often considered an extended application after the face tracking task has already been performed. This often involves passing the resultant 2D data through a simpler algorithm that best fits the data to a static 3D model to determine the 3D pose estimate. This work describes the 2.5D constrained local model, combining a deformable 3D shape point model with 2D texture information to provide direct estimation of the pose parameters, avoiding the need for additional optimization strategies. It achieves this through an analytical derivation of a Jacobian matrix describing how changes in the parameters of the model create changes in the shape within the image through a full-perspective camera model. In addition, the model has very low computational complexity and can run in real-time on modern mobile devices such as tablets and laptops. The point distribution model of the face is built in a unique way, so as to minimize the effect of changes in facial expressions on the estimated head pose and hence make the solution more robust. Finally, the texture information is trained via local neural fields—a deep learning approach that utilizes small discriminative patches to exploit spatial relationships between the pixels and provide strong peaks at the optimal locations. [ABSTRACT FROM AUTHOR]

Fire is one of the most dangerous disasters threatening human life and property globally. In order to reduce fire losses, researches on video analysis for early smoke detection have become particularly significant. However, it is still a challenging task to extract stable features for smoke recognition, largely due to its variations in color, shapes and texture. Classical convolutional neural networks can automatically learn feature representations of appearance from a single frame but fail to capture motion information between frames. For addressing this issue, in this paper, we propose a spatial-temporal based convolutional neural network for video smoke detection, and for real-time detection, propose an enhanced architecture, which utilizes a multitask learning strategy to jointly recognize smoke and estimate optical flow, capturing intra-frame appearance features and inter-frame motion features simultaneously. The effectiveness and efficiency of our proposed method is validated by experiments carried out on our self-created dataset, which achieves 97.0% detection rate and 3.5% false alarm rate with processing time of 5ms per frame, obviously outperforming existing methods. [ABSTRACT FROM AUTHOR]

This article is a systematic collection of existing methods and techniques for evaluating rendering category in the field of computer graphics. The motive for doing this study was the difficulty of selecting appropriate methods for evaluating and validating specific results reported by many researchers. This difficulty lies in the availability of numerous methods and lack of robust discussion of them. To approach such problems, the features of well-known methods are critically reviewed to provide researchers with backgrounds on evaluating different styles in photo-realistic rendering part of computer graphics. There are many ways to evaluating a research. For this article, classification and systemization method is use. After reviewing the features of different methods, their future is also discussed. Finally, dome pointers are proposed as to the likely future issues in evaluating the research on realistic rendering. It is expected that this analysis helps researchers to overcome the difficulties of evaluation not only in research, but also in application. [ABSTRACT FROM AUTHOR]

We present an end-to-end pipeline for the export of 3D scenes from content creation tools to a real-time rendering engine in an embeddable web-page, including a novel system for compression/decompression of textured polygonal meshes. We show that the compression/decompression outperforms the best state-of-the-art non-progressive alternative, especially as bandwidth increases, showing that web-specific techniques should consider the whole user pipeline. Our pipeline also includes progressivity, which is paramount for a good interactive user experience, and permits full user interaction with lower resolution versions of the 3D scenes, while progressively higher resolution data is downloaded. Finally, we discuss how our method may be used in the future to facilitate the transfer of animated meshes. [ABSTRACT FROM AUTHOR]

The ray marching method has become the most attractive method to provide realism in rendering the effects of light scattering in the participating media of numerous applications. This has attracted significant attention from scientific community. Up-sampling of ray marching method is suitable for rendering light shafts of realistic scenes, but suffers of consume a lot of time for rendering. Therefore, some encouraging outcomes have been achieved by using down-sampling of ray marching approach to accelerate rendered scenes. However, these methods are inherently prone to artifacts, aliasing and incorrect boundaries due to the reduced number of sample points along view rays. This research proposes a realistic real-time technique to generate soft light shafts by making use downsampling of ray marching in generating light shafts. The bilateral filtering is then applied to overcome all defects that caused by downsampling process to make a scene with smoothing transition while preserving on the edges. The contribution of this technique is to improve the boundaries of light shafts taking into account the effect of shadows. This technique allows obtaining soft marvelous light shafts, having a good performance and high quality. Thus, it is suitable for interactive applications. [ABSTRACT FROM AUTHOR]

Several algorithms have been introduced to render motion blur in real time by solving the visibility problem in the spatial-temporal domains. However, some algorithms render at interactive frame rates but have artifacts or noise. Therefore, we propose a new algorithm that renders real-time motion blur using extruded triangles. Our method uses two triangles in the previous frame and the current frame to make an extruded triangle then send it to rasterization. By using the standard rasterization, visibility determination is performed efficiently. To solve the occlusion between extruded triangles for a given pixel, we introduce a combination solution using a sorting in front-to-back order and bitwise operations in the spatial-temporal dimensions. This solution ensures that only non-occluded extruded triangles are shaded. We further improve performance of our algorithm using a coverage map. [ABSTRACT FROM AUTHOR]

Traditional dehazing techniques, as a well studied topic in image processing, are now widely used to eliminate the haze effects from individual images. However, the state-of-the-art dehazing algorithms may not provide sufficient support to video analytics, as a crucial pre-processing step for video-based decision making systems (e.g., robot navigation), due to poor coherence and low processing efficiency of the present algorithms. This paper presents a new framework, particularly designed for video dehazing, to output coherent results in real time, with two novel techniques. Firstly, we decompose the dehazing algorithms into three generic components, namely transmission map estimator, atmospheric light estimator and haze-free image generator. They can be simultaneously processed by multiple threads in the distributed system, such that the processing efficiency is optimized by automatic CPU resource allocation based on the workloads. Secondly, a cross-frame normalization scheme is proposed to enhance the coherence among consecutive frames, by sharing the parameters of atmospheric light from consecutive frames in the distributed computation platform. The combination of the above three components enables our framework to generate highly consistent and accurate dehazing results in real-time, by using only 5 PCs connected by Ethernet. [ABSTRACT FROM AUTHOR]

Interactive storytelling systems usually adopt computer graphics to represent virtual story worlds, which facilitates the dynamic generation of visual content. However, the quality of the images and motion produced by these systems is still inferior compared to the high quality experience found in live-action films. Interactive rates in photorealistic rendering for the film industry will not be possible for decades to come. A promising alternative is the replacement of 3D virtual characters with video sequences with real actors. In this paper, we propose a new method for video-based interactive narratives that uses video compositing algorithms that run at truly interactive frame rates. The proposed method is consistent with plots that are generated by nondeterministic planning algorithms. Moreover, we propose a system of artificial intelligent agents that perform the same roles played by filmmaking professionals. A user evaluation of the proposed method is presented. We believe that future improvements of the techniques proposed in this paper represent an important contribution to the quest for new and more immersive forms of interactive cinema. [ABSTRACT FROM AUTHOR]

We present an approach for real-time pen-and-ink hatching renderings on large scenes. Starting with 3D models including photorealistic textures and materials, we aim to propose a solution that produces hatched renderings. As we consider scene objects described as polygonal meshes with their own textures, we produce once hatching patterns at different tones and resolutions considering the material of each object. To achieve that, we create a flow direction map per texture pixel, using contour characteristics extracted from the original texture and then interpolated. Stroke trajectories are thus generated depending on the flow direction and using B-splines, providing tones from light-to-dark. Tones are then stored in a mutli-resolution tonal art map. Moreover, we aim to overcome the limitations of existing hatching rendering methods by introducing an illumination model, fully implemented on GPU and able to manage three shading types: regular shadow, soft/cast shadow and self-shadowing. Tones and hatching resolutions are, therefore, assigned according to local/global illumination supporting multiple light sources. Our model, both dedicated for 3D static model renderings and 3D model animation, supports model deformations and is also spatially and temporally coherent since it gives continuous hatching strokes during object animations and/or light displacements. [ABSTRACT FROM AUTHOR]

The Internet is the primary means for multimedia content sharing, playing a central role in the lifestyle of users. As a consequence, in the past few years, the traffic demand for access and edge networks has increased (video stream downloading, videoconferencing or even the broadcasting of video streams through the Internet), since multimedia applications have strict requirements, including high bandwidth, small amount of loss and low delay. To address this scenario, the edge as a service (EaaS) paradigm arises as a suitable approach to increasing the quality of Internet access. The EaaS uses network virtualization and software-defined networks to improve the resource utilization and manageability. Within this context, this article proposes a framework to manage the virtual network resource (VNR) according to the multimedia application characteristics, and not only the network requirements. Additionally, a study about the relationship between quality of experience (QoE) and VNR availability was performed to be used as a basis for a proposed resource allocation adjustment mechanism. Experiments using real multimedia traffic under distinct scenarios demonstrate the effectiveness of the proposed framework to ensure the QoE of users through the management of the VNR. [ABSTRACT FROM AUTHOR]

A Modified Dual Fusion (MDF) technique of image encryption is proposed in this paper to overcome the limitations that exist in the original research work of Q. Zhang et al. (Optik 124:3596-3600, 2013). A novel technique of DNA encoding is applied through chaotic maps on pixel level and SHA-256 hash of the plain image is used to generate secret keys to avoid chosen-plaintext attack. Also, in the modified scheme, two random images are generated from chaotic maps to fuse with the plain image after permutation in digital and DNA domains using XOR and addition operations respectively. The simulated experimental results and security analysis show that the proposed cryptosystem has fairly good encryption effect than the original fusion scheme but also has the capability to sustain noise which gets add during transmission over noisy channel. Besides, the paramount factor of improved scheme is suitable for the real time applications. [ABSTRACT FROM AUTHOR]

We present a simple and effective method for constructing a gallery that consists of weathering effect elements called time-dependent appearance manifolds (TDAMs). Since TDAMs are computed from sample video clips showing dynamic weathering phenomena, they represent very smooth changes in the appearance of weathered pixels over time. Once a gallery with a variety of weathering effects is prepared, users can interactively choose and apply the predefined effects onto the surface of 3D graphic models and then finally assign the most appropriate one. This video-based weathering method can be implemented with very simple algorithms and it supports predictable, intuitive, and natural effects. Our system allows users to produce photorealistic augmented videos that include 3D graphic models weathered by our method. Moreover, users can easily enhance the realism of the augmented videos by manipulating rendering parameters such as the degree of weathering, texturing, lighting, and shadowing through user-friendly graphical user interfaces (GUIs). [ABSTRACT FROM AUTHOR]

With increasing numbers of flights worldwide and a continuing rise in airport traffic, air-traffic management is faced with a number of challenges. These include monitoring, reporting, planning, and problem analysis of past and current air traffic, e.g., to identify hotspots, minimize delays, or to optimize sector assignments to air-traffic controllers. To cope with these challenges, cyber worlds can be used for interactive visual analysis and analytical reasoning based on aircraft trajectory data. However, with growing data size and complexity, visualization requires high computational efficiency to process that data within real-time constraints. This paper presents a technique for real-time animated visualization of massive trajectory data. It enables (1) interactive spatio-temporal filtering, (2) generic mapping of trajectory attributes to geometric representations and appearance, and (3) real-time rendering within 3D virtual environments such as virtual 3D airport or 3D city models. Different visualization metaphors can be efficiently built upon this technique such as temporal focus+context, density maps, or overview+detail methods. As a general-purpose visualization technique, it can be applied to general 3D and 3+1D trajectory data, e.g., traffic movement data, geo-referenced networks, or spatio-temporal data, and it supports related visual analytics and data mining tasks within cyber worlds. [ABSTRACT FROM AUTHOR]

In most realtime applications such as 3D games, in order to reduce the complexity of the scene being rendered, objects are often made by simple and large primitives. Thus, the phenomenon of edge highlighting, which would require chamfering structures made by lots of small patches at the seaming, is absent and is often faked by 'highlights' drawn on the texture. We proposed a realistic realtime rendering procedure for highlighting chamfering structures, or rounded edges, by considering specified edges as thin cylinders and obtained the intensity via integration. We derived a brief approximated formula generalized from Blinn's shadow model, and used a precomputed integration table to accelerate the render speed and reduce resources needed. The algorithm is implemented with shader language, and can be considered as a post-process on original result. Evaluation shows that the effect on rendering speed is limited even for scenes with large scale of vertices. [ABSTRACT FROM AUTHOR]

Street-level visualization is an important application of 3D city models. Challenges to street-level visualization include the cluttering of buildings due to fine detail and visualization performance. In this paper, a novel method is proposed for street-level visualization based on visual saliency evaluation. The basic idea of the method is to preserve these salient buildings in a scene while removing those that are non-salient. The method can be divided into pre-processing procedures and real-time visualization. The first step in pre-processing is to convert 3D building models at higher Levels of Detail (LoDs) into LoD1 models with simplified ground plans. Then, a number of index viewpoints are created along the streets; these indices refer to both the position and the direction of each street site. A visual saliency value is computed for each building, with respect to the index site, based on a visual difference between the original model and the generalized model. We calculate and evaluate three methods for visual saliency: local difference, global difference and minimum projection area. The real-time visualization process begins by mapping the observer to its closest indices. The street view is then generated based on the building information stored in those indexes. A user study shows that the local visual saliency method performs better than do the global visual saliency, area and image-based methods and that the framework proposed in this paper may improve the performance of 3D visualization. [ABSTRACT FROM AUTHOR]

We present a novel approach for real-time rendering Loop subdivision surfaces on modern graphics hardware. Our algorithm evaluates both positions and normals accurately, thus providing the true Loop subdivision surface. The core idea is to recursively refine irregular patches using a GPU compute kernel. All generated regular patches are then directly evaluated and rendered using the hardware tessellation unit. Our approach handles triangular control meshes of arbitrary topologies and incorporates common subdivision surface features such as semi-sharp creases and hierarchical edits. While surface rendering is accurate up to machine precision, we also enforce a consistent bitwise evaluation of positions and normals at patch boundaries. This is particularly useful in the context of displacement mapping which strictly requires matching surface normals. Furthermore, we incorporate efficient level-of-detail rendering where subdivision depth and tessellation density can be adjusted on-the-fly. Overall, our algorithm provides high-quality results at real-time frame rates, thus being ideally suited to interactive rendering applications such as video games or authoring tools. [ABSTRACT FROM AUTHOR]

Whereas 3D surface models are often used for augmented reality (e.g., for occlusion handling or model-based camera tracking), the creation and the use of such dense 3D models in augmented reality applications usually are two separated processes. The 3D surface models are often created in offline preparation steps, which makes it difficult to detect changes and to adapt the 3D model to these changes. This work presents a 3D change detection and model adjustment framework that combines AR techniques with real-time depth imaging to close the loop between dense 3D modeling and augmented reality. The proposed method detects the differences between a scene and a 3D model of the scene in real time. Then, the detected geometric differences are used to update the 3D model, thus bringing AR and 3D modeling closer together. The accuracy of the geometric difference detection depends on the depth measurement accuracy as well as on the accuracy of the intrinsic and extrinsic parameters. To evaluate the influence of these parameters, several experiments were conducted with simulated ground truth data. Furthermore, the evaluation shows the applicability of AR and depth image-based 3D modeling for model-based camera tracking. [ABSTRACT FROM AUTHOR]

Every picture tells a story. In photography, the story is portrayed by a composition of objects, commonly referred to as the subjects of the piece. Were we to remove these objects, the story would be lost. When manipulating images, either for artistic rendering or cropping, it is crucial that the story of the piece remains intact. As a result, the knowledge of the location of these prominent objects is essential. We propose an approach for saliency detection that combines previously suggested patch distinctness with an object probability map. The object probability map infers the most probable locations of the subjects of the photograph according to highly distinct salient cues. The benefits of the proposed approach are demonstrated through state-of-the-art results on common data sets. We further show the benefit of our method in various manipulations of real-world photographs while preserving their meaning. [ABSTRACT FROM AUTHOR]

In this paper, an efficient deformation framework is presented for skeleton-driven polygonal characters. Standard solutions, such as linear blend skinning, focus on primary deformations and require intensive user adjustment. We propose constructing a lattice of cubic cells embracing the input surface mesh. Based on the lattice, our system automatically propagates smooth skinning weights from bones to drive the surface primary deformation, and it rectifies the over-compressed regions by volume preservation. The secondary deformation is, in the meanwhile, generated by the lattice shape matching with dynamic particles. The proposed framework can generate both low- and high-frequency surface motions such as muscle deformation and vibrations with few user interventions. Our results demonstrate that the proposed lattice-based method is liable to GPU computation, and it is adequate to real-time character animation. [ABSTRACT FROM AUTHOR]

Polluted water is very common in our world. Vividly rendering polluted water can bring people real, different, and fancy feelings. Especially in under water imagery, taking polluted water into consideration will produce more plausible results. Polluted water consists of many kinds of pollutants, which interact with light differently and make water look turbid. The optical properties of polluted water change with the concentrations of pollutants significantly. In this paper, we provide a method to obtain the optical properties of polluted water, which makes a bio-optical model for polluted water and connects the optical parameters with water quality data, i.e., the concentrations of pollutants. Our method can estimate the optical properties of polluted water regardless of the kinds and the concentrations of pollutants in water. Polluted water is inhomogeneous and has multiple scattering effects. We use volumetric photon mapping to render it and provide a 3D weight-varying radiance estimate method for the photon mapping. This radiance estimate method can compute high-frequency effects easily, which can show more details of the pollution process. Experiments demonstrate that our approach can generate polluted water effects unachievable by standard rendering methods. [ABSTRACT FROM AUTHOR]

Light baking has long been a popular technique for real-time rendering. It usually precomputes and bakes the global lighting effects as vertex attributes or textures. Vertex baking requires less memory but can cause artifacts for large triangles. Texture baking can avoid this and generate a high-quality visual effect in real-time rendering. However, it requires significant memory consumption, which may limit the real-time performance and usage. To address this problem, we propose an adaptive mesh subdivision algorithm for memory-efficient light baking, including a fast triangle subdivision level determination method and an optimized solution to calculate vertex colors. Only the subdivided mesh is required during the real-time rendering. Therefore, memory requirements can be significantly reduced while keeping the visual effect. Besides, the subdivision level is allowed to be intuitively controlled by users with a specified parameter. Our algorithm can be easily implemented on commodity graphics hardware and integrated in existing real-time applications such as online preview systems. [ABSTRACT FROM AUTHOR]

Maximum Intensity Difference Accumulation (MIDA) combines the advantage of Direct Volume Rendering (DVR) and Maximum Intensity Projection (MIP). However, many features with local maximum intensity are still missing in the final rendering image. This paper presents a novel approach to focus on features with local maximum intensity within the dataset. Moving Least Squares (MLS) is used to smooth each ray profile during the raycasting in order to eliminate noise in the data and to highlight significant transition points on the profile. We then adopt a local minimum-point searching method to analyze the ray profile, and identify the transition points that mark the local maximum intensity points within the dataset. At the rendering stage, we implement a novel local intensity difference accumulation (LIDA) to accumulate the colors and opacity. Surface shading is introduced to improve the spatial cues of the features. We also employ tone-reduction to preserve the original local contrast. Our approach can highlight local features in the dataset without involving the adjustment of transfer functions. The experiments demonstrate high-quality rendering results at an interactive frame rate. [ABSTRACT FROM AUTHOR]

Large-scale remote sensing images, including both satellite and aerial photographs, are widely used to render terrain scenes in real-time geographic visualization systems. Such systems often require large memories in order to store fine terrain details and fast network speeds to transfer image data, if they are built as web applications. In this paper, we propose a progressive texture compression framework to reduce the memory and bandwidth cost by compressing repeated content within and among large-scale remote sensing images. Different from existing image factorization methods, our algorithm incrementally find similar regions in new images so that large-scale images can be more efficiently compressed over time. We further propose a descriptor, the Gray Split Rotate (GSR) descriptor, to accelerate the similarity search. The reconstruction quality is finally improved by compressing residual error maps using customized S3TC-like compression. Our experiment shows that even with the error maps, our system still has higher compression rate and higher compression quality than using S3TC alone, which is a typical compression solution in most existing visualization systems. [ABSTRACT FROM AUTHOR]

Realistic talking heads have important use in interactive multimedia applications. This paper presents a novel framework to synthesize realistic facial animations driven by motion capture data using Laplacian deformation. We first capture the facial expression from a performer, then decompose the motion data into two components: the rigid movement of the head and the change of the facial expression. By making use of the local-detail preserving property of the Laplacian coordinate, we clone the captured facial expression onto a neutral 3D facial model using Laplacian deformation. We choose some expression 'independent points' in the facial model as the fixed points when solving the Laplacian deformation equations. Experimental results show that our approach can synthesize realistic facial expressions in real time while preserving the facial details. We compare our method with the state-of-the-art facial expression synthesis methods to verify the advantages of our method. Our approach can be applied in real-time multimedia systems. [ABSTRACT FROM AUTHOR]

Rendering global illumination for objects with mesostructure surfaces is a time-consuming task, and cannot presently be applied to interactive graphics. This paper presents a real-time rendering method based on a mesostructure height gradient map (MHGM) to exhibit lighting effects on meso-scale details in dynamic environments. We approximate global illumination using a lighting model including three components: incident ambient light, direct light and single bounce indirect light. MHGM is introduced to create local apex sets, which would help us to compute the three components adaptively. Our approach runs entirely on the graphics hardware, and uses deferred shading and the graphics pipeline to accelerate computation. We achieve high quality results which can render meso-scale details with approximate global illumination even for low-resolution geometric models. Moreover, our approach fully supports dynamic scenes and deformable objects. [ABSTRACT FROM AUTHOR]

This paper presents an implementation of the Active Appearance Model that is able to track a face on a mobile device in real-time. We achieve this performance by discarding an explicit texture model, using fixed-point arithmetic for much of the computation, applying a sequence of models with increasing complexity, and exploiting a sparse basis projection via Haar-like features. Our results show that the Haar-like feature basis achieves similar performance to more traditional approaches while being more suitable for a mobile device. Finally, we discuss mobile applications of the system such as face verification, teleconferencing and human-computer interaction. [ABSTRACT FROM AUTHOR]

Real time rendering of three-dimensional scenes in high photorealistic details is a hard task, such as in the ray tracing rendering algorithm. In general, the performance achieved by a sequential software-based implementation of ray tracing is far from satisfactory. However, parallel implementations of ray tracing have been enabling reasonable real time performance, as the algorithm is embarrassingly parallel. Thus, a custom parallel design in hardware is likely to achieve an even higher performance. In this paper, we propose a hardware parallel architecture capable of dealing with the main desirable features of ray tracing, such as shadows and reflection effects, imposing low area cost and a promising rendering performance. Such architecture, called GridRT, is based on the Uniform Grid acceleration structure and is intended to deliver massive parallelism through parallel ray-triangle intersection tests as well as parallel processing of many rays. A hardware implementation of the proposed architecture is presented, together with some performance results and resources requirements. The rendering is reduced by 80% using a grid configuration of eight processing elements. [ABSTRACT FROM AUTHOR]

In this paper we present a novel GPU-oriented method of creating an inherently continuous triangular mesh for tile-based rendering of regular height fields. The method is based on tiling data-independent semi-regular meshes of non-uniform structure, a technique that is quite different from other mesh tiling approaches. A complete, memory efficient set of mesh patterns is created by an off-line procedure and stored into the graphics adapter's memory at runtime. At rendering time, for each tile, one of the precomputed mesh patterns is selected for rendering. The selected mesh pattern fits the required level of details of the tile and ensures seamless connection with other adjacent mesh patterns, like in a game of dominoes. The scalability potential of the proposed method is demonstrated through quadtree hierarchical grouping of tiles. The efficiency is verified by experimental results on height fields for terrain representation, where the method achieves high frame rates and sustained triangle throughput on high resolution viewports with sub-pixel error tolerance. Frame rate sensitivity to real-time modifications of the height field is measured, and it is shown that the method is very tolerant and consequently well tailored for applications dealing with rapidly changeable phenomena represented by height fields. [ABSTRACT FROM AUTHOR]

This paper revisits the problem of wireframe rendering, which, at first, appears to be an easily solved problem. However, the conventional solution is inefficient and does not result in high-quality images. Recently, graphics hardware programming has been employed to achieve high-quality solid line rendering. In this paper, we present a simpler and faster technique for wireframe rendering based on texture mapping. Our technique does not require (but can benefit from) graphics hardware programming and thus can be easily integrated into existing rendering engines, while resulting in fast, accurate, high-quality, anti-aliased, and still versatile, wireframe drawing. For topologically structured meshes, our approach allows the rendering of wireframe decoupled from the underlying mesh, making possible the rendering of original wireframes on top of decimated meshes. [ABSTRACT FROM AUTHOR]

Texture mapping is an important technique for adding visual details to geometric models. Image-based texture mapping is the most popular approach, but it relies on pre-computed images which often limit their use to static effects. For adding dynamic effects, procedural-based texturing is more adequate. Since it rely on functions to describe texturing patterns, procedural texturing allows for a more compact representation and control of visual effects by a simple change of parameters. In this work we describe GeoTextures, an approach that uses geodesic distance fields defined from multiple sources at different locations over a model surface to place, advect, and combine procedural visual effects over complex surfaces. The use of geodesics extends the scope of common procedural textures which are usually limited to using spatial 3D coordinates or 2D texture coordinates. We illustrate the flexibility of our real-time approach with a range of visual effects, such as time-based propagation of weathering phenomena, transparency effects, and mesh displacement over surfaces with smooth silhouettes using hardware based tessellation available in current graphics cards. [ABSTRACT FROM AUTHOR]

Non-photorealistic (illustrative) rendering augments typical rendering models to selectively emphasize or de-emphasize specific structures of rendered objects. Illustrative techniques may affect not only the rendering style of specific portions of an object but also their visibility, ensuring that less important regions do not occlude more important ones. Cutaway views completely remove occluding, unimportant structures-possibly also removing valuable context information-while existing solutions for smooth reduction of occlusion based on importance lack precise visibility control, simplicity and generality. We introduce a new front-to-back fragment composition equation that directly takes into account a measure of sample importance and allows smooth and precise importance-based visibility control. We demonstrate the generality of our composition equation with several illustrative effects, which were obtained by using a set of importance measures calculated on the fly or defined by the user. The presented composition method is suitable for direct volume rendering as well as rendering of layered 3D models. We discuss both cases and show examples, though focusing mainly on illustration of volumetric data. [ABSTRACT FROM AUTHOR]

The objective of this paper is to adapt photon mapping for real-time simulation of caustics. High-performance algorithm adapted for the GPU and implemented on the basis of cross-platform OpenGL and OpenCL APIs is proposed. For effective rendering of caustics and generation of photon map OpenGL shaders are used. Voxel acceleration structure constructed directly on the GPU by means of OpenCL provides fast access to photon map. Performance estimation for different equipment is given. [ABSTRACT FROM AUTHOR]

This work presents an approach for biased photorealistic rendering on graphics processor units (GPUs). The key idea of the approach is to combine irradiance caching with coherent adaptive path tracing. [ABSTRACT FROM AUTHOR]

Turning the page is a mechanical part of the cognitive act of reading that we do literally unthinkingly. Interest in realistic book models for digital libraries and other online documents is growing. Yet, actually producing a computer graphics implementation for modeling page turning is a challenging undertaking. There are many possible foundations: two-dimensional models that use reflection and rotation; geometrical models using cylinders or cones; mass-spring models that simulate the mechanical properties of paper at varying degrees of fidelity; and finite-element models that directly compute the actual forces within a piece of paper. Even the simplest methods are not trivial, and the more sophisticated ones involve detailed physical and mathematical models. The variety, intricacy, and complexity of possible ways of simulating this fundamental act of reading is virtually unknown. This article surveys computer graphics models for page turning. It combines a tutorial introduction that covers the range of possibilities and complexities with a mathematical synopsis of each model in sufficient detail to serve as a basis for implementation. Illustrations are included, which are generated through our implementations of each model. The techniques presented include geometric methods (both two- and three-dimensional), mass-spring models with varying degrees of accuracy and complexity, and finite-element models. We include a detailed comparison of experimentally determined computation time and subjective visual fidelity for all the methods discussed. The simpler techniques support convincing real-time implementations on ordinary workstations. We also address the question of whether such techniques are worthwhile in practice by describing results from a user study that compared the performance of a page-turning book model with HTML and PDF presentations of the same material—and with physical books. This demonstrates that the book model has many advantages over conventional document formats. [ABSTRACT FROM AUTHOR]

Abstract  Adapting natural phenomena rendering for real-time applications has become a common practice in computer graphics. We propose a GPU-based multi-band method for optimized synthesis of “far from coast” ocean waves using an empirical Fourier domain model. Instead of performing two independent syntheses for low- and high-band frequencies of ocean waves, we perform only low-band synthesis and employ results to reproduce high frequency details of ocean surface by an optimized iterative up-sampling stage. Our experimental results show that this approach greatly improves the performance of original multi-band synthesis while maintaining image quality. [ABSTRACT FROM AUTHOR]

This paper describes novel methods for evoking a multichannel audio experience over stereo headphones. In contrast to theconventional convolution-based approach where, for example, five input channels are filtered using ten head-related transfer functions, the current approach is based on a parametric representation of the multichannel signal, along with either a parametric representation of the head-related transfer functions or a reduced set of head-related transfer functions. An audio scene with multiple virtual sound sources is represented by a mono or a stereo downmix signal of all sound source signals, accompanied by certain statistical (spatial) properties. These statistical properties of the sound sources are either combined with statistical properties of head-related transfer functions to estimate "binaural parameters" that represent the perceptually relevant aspects of the auditory scene or used to create a limited set of combined head-related transfer functions that can be applied directly on the downmix signal. Subsequently, a binaural rendering stage reinstates the statistical properties of the sound sources by applying the estimated binaural parameters or the reduced set of combined head-related transfer functions directly on the downmix. If combined with parametric multichannel audio coders such as MPEG Surround, the proposed methods are advantageous over conventional methods in terms of perceived quality and computational complexity. [ABSTRACT FROM AUTHOR]