We present the I3DC system prototype, which constructs the cube for tens of millions of data items within milliseconds, and provides high-quality cube visualization as well as highly-interactive OLAP operations. Our approach is based on a novel blending-as-aggregation (BAA) algorithm that maps distributive OLAP aggregations to the intrinsic rendering mechanisms of the GPU. Our system runs entirely on the GPU and requires no precomputations.

Recent research has shown promising results on using graphics processing units (GPUs) to accelerate general-purpose computation. However, today's GPUs do not support recursive functions. As a result, for inherently recursive algorithms such as tree traversal, GPU programmers need to explicitly use stacks to emulate the recursion. Parallelizing such stack-based implementation on the GPU increases the programming difficulty; moreover, it is unclear how to improve the efficiency of such parallel implementations. As a first step to address both ease of programming and efficiency issues, we propose three parallel stack implementation alternatives that differ in the granularity of stack sharing. Taking tree traversals as an example, we study the performance tradeoffs between these alternatives and analyze their behaviors in various situations. Our results could be useful to both GPU programmers and GPU compiler writers.

We present a new technique for interactive relighting of dynamic refractive objects with complex material properties. We describe our technique in terms of a rendering pipeline in which each stage runs entirely on the GPU. The rendering pipeline converts surfaces to volumetric data, traces the curved paths of photons as they refract through the volume, and renders arbitrary views of the resulting radiance distribution. Our rendering pipeline is fast enough to permit interactive updates to lighting, materials, geometry, and viewing parameters without any precomputation. Applications of our technique include the visualization of caustics, absorption, and scattering while running physical simulations or while manipulating surfaces in real time.

We present transparent Direct3D9 application-level parallel rendering system named D3DPR. It allows Direct3D9 application to run on graphics cluster with no modification. Graphics cluster can be classified as two types of logical node, i.e. resource distributing node (D-Node) and resource rendering node (R-Node) by D3DPR. Among them, D-Node is responsible for converting Direct3D9 application to four kinds of rendering resource including command stream, vertex stream, index stream and texture stream. R-Node is responsible for reconstructing Direct3D9 interface rendering command based on the description information and resource data of received rendering resource. Each R-Node reserves entire rendering resource and distributes rendering task by computing the projective screen region of multi-stream based scene data bounding box. Experimental results have demonstrated that D3DPR parallel rendering system can not only achieve high-resolution tiled display but also promote rendering performance for Direct3D9 application running on graphics cluster.

There are two problems in the existing rendering platforms that support HLA-based simulation applications. One is the fact that the management of simulation entity objects and the management of rendering scene objects are separate, which leads to inefficiency in simulation and rendering. Another one is absence of rendering interface, especially for parallel rendering for users. In order to solve the above problems, we present a unified object model supporting HLA-based simulation and parallel rendering, which consists of heterogenous scene graph tree, action list and universal access interface. The Unified object model establishes an efficient data exchange bridge between HLA simulation and parallel rendering. Therefore massive complex scene and large quantity of simulation entities can be organized and managed in a unified form. An experimental demo is given at the end of this paper.

Recently, graphics processing units, or GPUs, have become a viable alternative as commodity, parallel hardware for general-purpose computing, due to their massive data-parallelism, high memory bandwidth, and improved general-purpose programming interface. In this paper, we explore the use of GPU on the grid file, a traditional multidimensional access method. Considering the hardware characteristics of GPUs, we design a massively multi-threaded GPU-based grid file for static, memory-resident multidimensional point data. Moreover, we propose a hierarchical grid file variant to handle data skews efficiently. Our implementations on the NVIDIA G80 GTX graphics card are able to achieve two to eight times' higher performance than their CPU counterparts on a single PC.

Distributed simulation and parallel rendering based on PC cluster have seen great success in recent years. To improve the overall performance, there is a trend to integrate modeling, simulation and visualization into a common distributed environment. In this paper, we propose a unified framework of building high performance distributed virtual reality (DVR) applications. The core components of this framework include the High Level Architecture (HLA), scene graphs and parallel rendering. The HLA supports interactive distributed simulation. Scene graphs are efficient to organize and manipulate scene data. And parallel rendering provides powerful rendering ability. This paper presents the in-depth architectural analysis of each components and derives a design that integrates them into a unified framework. Two DVR applications, including a remote navigation of massive virtual scenes and a multi-player video game, have been developed to evaluate the framework performance.

Abstract Paper‐cut is one of the most characteristic Chinese folk arts, often used during festivals and celebrations. Chinese artists have used paper‐cut to make animations. Typical paper‐cut artwork is made with 2D illustrations on paper, and making many frames necessary for an entire animation can be tedious and expensive. We present a system that allows a designer to directly annotate a 3D model with paper‐cut patterns, while still allowing for adding an artistic touch to the design. We have designed special motifs coupled with templates, resulting in a parameterized set of decorative paper‐cut patterns which give the artist flexible control and allow editing of the pattern size, orientation, and shape. The artist chooses a pattern and places the pattern on the model in the desired position. The system determines actual surface coverage and trims the object's surface geometry to simulate the cut‐out effect we observe in traditional 2D paper‐cut art. We demonstrate that our system allows faster and easier addition of paper‐cut decoration to 3D models compared to general purpose modeling tools, such as Maya. Animations made with the 3D paper‐cut models escape from the limitations of traditional 2D paper‐cut animation on the movement in perspective, furthermore, our system allows for easy pattern animations on 3D models, which is very powerful but hard to do with traditional paper‐cut animation. Copyright © 2007 John Wiley & Sons, Ltd.

Abstract Parallel rendering, visibility culling and level‐of‐detail are key techniques to improve the rendering performance for large geometric data sets. Although each of these techniques has been researched extensively and some systems have been developed to combine them together. However, parallel occlusion culling, that is distributing the computation of occlusion culling to multiple computing nodes such as a CPUs cluster or a GPUs cluster, has rarely been touched. This is because most existing occlusion culling algorithms are difficult to parallelize or do not scale well when parallelized. We first introduce a novel occlusion culling algorithm that uses the occlusion query functionality provided by current GPU. We employ a visibility prediction technique based on temporal coherence to reduce the times of occlusion query. Furthermore, different strategies of parallelizing the occlusion culling algorithm on a GPUs cluster are proposed including data parallelism strategies and functionality parallelism strategies. Data parallelism strategies decompose the data sets for occlusion query into disjoint parts and map these queries on different cluster nodes for parallel execution while functionality parallelism strategies assemble an occlusion culling pipeline with multiple cluster nodes which outputs image stream steadily. We propose a number of solutions to some special issues on parallelizing this occlusion culling algorithm, such as the transferring of data dependency and the load‐balancing of occlusion culling pipeline. Experimental results demonstrate the efficiency of the proposed parallelism strategies of the occlusion culling algorithm based on the visibility predictor. Copyright © 2007 John Wiley & Sons, Ltd.

We present a technique for interactive relighting in which source radiance, viewing direction, and BRDFs can all be changed on the fly. In handling dynamic BRDFs, our method efficiently accounts for the effects of BRDF modification on the reflectance and incident radiance at a surface point. For reflectance, we develop a BRDF tensor representation that can be factorized into adjustable terms for lighting, viewing, and BRDF parameters. For incident radiance, there exists a non-linear relationship between indirect lighting and BRDFs in a scene, which makes linear light transport frameworks such as PRT unsuitable. To overcome this problem, we introduceprecomputed transfer tensors(PTTs) which decompose indirect lighting into precomputable components that are each a function of BRDFs in the scene, and can be rapidly combined at run time to correctly determine incident radiance. We additionally describe a method for efficient handling of high-frequency specular reflections by separating them from the BRDF tensor representation and processing them using precomputed visibility information. With relighting based on PTTs, interactive performance with indirect lighting is demonstrated in applications to BRDF animation and material tuning.

In this paper we propose an efficient system for rendering large terrain data in a cluster environment. Both geometry and texture data are stored in the server, constructed and optimized as pre-computed static quadtree. Hierarchical view frustum culling and view-dependent texture and geometry refinement is performed through a top-down traversal algorithm in the client. We guarantee overall geometric continuity and exploit programmable graphics hardware to achieve low CPU overload and high triangles throughput. Speculative terrain data prefetching is exploited for hiding network delay. Large datasets can be rendered in real-time with our system and the performance is almost independent of the dataset size.

This paper presents an efficient algorithm for alpha estimation based on perceptual color space in natural image matting. A user specifies a trimap which partitions an image into definitely foreground, definitely background and unknown. For each pixel in the unknown region, the algorithm separates intensity and chroma information from RGB color after its foreground and background color components are estimated. Consequently, the alpha component is decomposed into intensity part and chroma part. The weighted mean of these two parts yields the final alpha value. Experimental results demonstrate the efficiency and advantage of the proposed algorithm over other approaches.

We present a system for decorating arbitrary surfaces with bidirectional texture functions (BTF). Our system generates BTFs in two steps. First, we automatically synthesize a BTF over the target surface from a given BTF sample. Then, we let the user interactively paint BTF patches onto the surface such that the painted patches seamlessly integrate with the background patterns. Our system is based on a patch-based texture synthesis approach known as quilting. We present a graphcut algorithm for BTF synthesis on surfaces and the algorithm works well for a wide variety of BTF samples, including those which present problems for existing algorithms. We also describe a graphcut texture painting algorithm for creating new surface imperfections (e.g., dirt, cracks, scratches) from existing imperfections found in input BTF samples. Using these algorithms, we can decorate surfaces with real-world textures that have spatially-variant reflectance, fine-scale geometry details, and surfaces imperfections. A particularly attractive feature of BTF painting is that it allows us to capture imperfections of real materials and paint them onto geometry models. We demonstrate the effectiveness of our system with examples.

Recently, the graphics processing capabilities of graphics systems have improved a lot, and more and more information must be presented to the users. While the display resolution of monitors is still what it is 20 years ago, and becomes the bottleneck of visualization. This leads to recent interest in the research for high-resolution displays. One great solution is to use multiple projectors tiled together to form a large logical display wall and provide high display resolutions and large physical display sizes. This paper presents a survey of the construction process of these kinds of multi-projector tiled display wall systems. The hardware construction problem is first explored. And then we describe the two most important problems of multi-projector tiled display wall systems, i.e. geometric calibration and photometric calibration of projectors. Various algorithms are addressed and compared. Lastly, an introduction of the high resolution image generation via distributed rendering is presented.

Tour into the picture (TIP) is a technique that makes animation of a scene from single image. The size of TIP box model, as well as the positions of foreground objects in the model can be calculated by relative depth calculation. To simulate an incline in the image, an algorithm is proposed by us to calculate the slope and the length of an incline model. After that, we present an algorithm that successfully makes integration of TIP and panorama to perform joint multi-scene rendering in our virtual tour system. Our virtual tour system shows that these techniques have achieved very satisfactory results.

An algorithm is presented for effectively, estimating alpha based on perceptual color space in natural image matting. After the foreground and background color components of given observed unknown pixel are estimated, our alpha estimating algorithm separates intensity and chroma information of RGB color, i.e, alpha is decomposed into intensity alpha and chroma alpha. Then we take the weighted mean over these two alpha values as the final alpha. Matte results and the comparison with the other alpha estimating algorithms in natural image matting are given in this paper.

Realistic audio rendering is an integral part of any immersive multimedia applications. A progressive sound-rendering scheme, which integrates sound source modeling with sound transmission simulation, is proposed to generate D sound effects for multimedia applications. At first, sound source modeling is performed through either sinusoidal analysis of prerecorded sound or modal analysis of virtual object based on its geometry and material properties. Then, all the sub components derived are sorted according to perceptual criteria. Dependent on resource availability, the afterwards real time synthesis can be done in a progressive way and binaural filtering is integrated into this process directly

Abstract In this paper, we propose a real‐time method for rendering soft shadows and inter‐reflections of dynamic objects under complex illumination. In previous methods, many efforts were taken to acquire occlusion and reflection informations for dynamic scene on the fly, and the result image cannot be generated in real time. In our approach, these informations for each object are pre‐computed and stored in well‐defined Spherical Radiance Transport Maps (SRTMs). For distant complex illumination such as environment illumination and area light source, we decompose the illumination to several hundred directional lights. In rendering, we search in SRTMs for occlusion info which may cause shadows, and reflection info which may cause inter‐reflections. Finally we produce realistic soft shadows and inter‐reflections efficiently. Our method is related with but different from previous Pre‐computed Radiance Transfer techniques which are only suitable for static scene. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: shading and shadowing

The geometric constraint, which is called corner structure, is studied. Firstly, the corner structure in one image is introduced to calculate the initial solutions of the intrinsic and extrinsic parameters of the camera. Then the solutions are optimized via minimizing the differences between the observed points and the reprojections under the geometric constraints in two images. Because only one image is used when the initial solutions are computed, the critical motion sequences can be avoided, and then the degeneracies in camera self-calibration can be avoided. The precisions of the calculated parameters are improved because the geometric structures in two images are used in optimization. The experimental results demonstrate that our algorithm is robust.

We propose a new physically-based model for real-time animation of draped cloth which not only speeds up the rendering greatly, but also maintains visually appealing results. Our simplified model is represented as a grid object composed of mass points connected by semi-rigid rods, whose behavior is governed by non-rigid dynamics. The longitudinal (vertical) and latitudinal (horizontal) directions of our model are decoupled and processed separately, and later combined to generate the final cloth. Moreover, we provide a uniform treatment of internal and external forces.

Navigation path planning is a crucial part of virtual endoscopy, but the identification of the optimal fly-through path is a time-intensive process. This paper describes a prototype system for virtual endoscopy and proposes a slice-based approach to calculating the path of the virtual camera that uses the slice borderlines of region-of-interest images to obtain the approximate centreline, centralised locally with respect to the hollow object wall. By using the 2D slice borderlines to express the hollow object boundary, the path searching and polygon intersection computing are simplified and made more efficient. Finally, we present results of our algorithm tested on the Visible Human data set.

This paper presents a feature-based approach to the automatic generation of an injection mold. In the approach, all the molding features of a molded part are recognized first using a universal hint-based feature recognition algorithm, and the optimal parting direction is determined based on the feature model. Then, all the faces related with the parting line are classified into three groups according to the determined parting direction, and two kinds of parting lines are automatically determined by extracting the largest profile of each face group. Finally, the parting surface is generated based on the optimal pacing line, thereafter the mold core and mold cavity are automatically set up by splitting the mold box of the molded part with the generated parting surface. By using recognized molding features, the approach makes it possible to identify all undercuts, to determine internal parting lines and internal parting surfaces, to generate the mold core and cavity of a complex molded part with undercuts as well.

In this paper we present a new BSP (Binary Space Partitioning (BSP) tree. BSP trees are one of the most successful space partitioning techniques, since they allow both object modeling and classification in one single structure. In this paper, we present a new framework designed for a multi-resolution modeling system that incorporates the BSP tree structure and dynamic levels of detail models. It has the advantages of both BSP and multi-resolution representations. The tree construction and traversal routines for the multi-resolution BSP tree are discussed in detail. Images and timing for our implementation are provided.

The steady growth of the Internet has dramatically changed the way information is shared and modern users expect near real time delivery, high quality images together with in-depth navigation and exploration of 3D models. Multiresolution is a promising approach for fast distributed volume visualisation employing levels-of-detail. We review multiresolution algorithms and visualisation systems on the WWW. Our discussion is based on experience gained in the development of the IAEVA-II project funded by the European Commission. A new method for rapid data classification/rendering of multiresolution volumes based on shear-warp factorisation, is described. We can change classification functions and data resolution during rendering without significant reduction in interactivity. A method for constructing multiresolution transfer functions for determining opacity is also investigated. Finally, future trends in developing WWW visualisation systems are discussed.

In many applications of scientific visualization, the data fields are so large that they are very expensive to store, transmit and render. Multiresolution offers a promising new approach for addressing these difficulties on a simple, unified way. Wavelets provide an extremely useful mathematical toolkit for hierarchically decomposing functions in ways that are both efficient and theoretically sound. This paper focuses on extension of wavelet based multiresolution to arbitrary topological data grid. Using wavelet transform, the method proposed here obtains a unique shape description of an irregular data field. A biorthogonal volume wavelet is constructed. Recursive subdivision is applied to irregular data field and leads to a collection of refinable scaling functions and hence to a sequence of nested linear spaces, as required by multiresolution. In order to overcome the subdivision connectivity restriction, an applicable method is presented to convert the completely arbitrary data field to multiresolution so that the technique for creating multiresolution can be used.

We put forward a marching cube algorithm based on the extraction and expression of multiresolution isosurfaces. It can solve the problem of too much and too meticulous triangular meshes on a traditional marching cube algorithm with single resolution. At the same time, under the users' requests, it can apply various precision to different regions of the object to get a compromise between rendering time and image precision. Our algorithm firstly, begins with low resolution images, and gradually extracts high precision isosurfaces from high resolution ones to achieve multiresolution rendering; finally, it establishes the corresponding relationship between different resolution isosurfaces and images. Specifically, the algorithms use a new 3D image encoding method: recursive subdivision wavelet encoding which is more suitable for extracting multiresolution isosurfaces.

We present a data flow based software platform called GIVE (General Interactive Visualization Environment). GIVE owns a data flow kernel, a visual programming interface and an extensible module library. It greatly enhances the efficiency of building visualization programs. GIVE has the following distinctive features: it introduces control nodes and procedure nodes into traditional data flow architecture, so it can support complex ViSC application: it is a well opened environment, supported by two efficient interactive tools-GIVE/ME (Module Extender) and GIVE/DE (Data Extender)-which enables users to extend modules and data types into the system freely and conveniently; and it has a module library composed of varieties of modules. We first introduce several concepts of the data flow architecture, then describe the designation of GIVE, and finally discuss the implementation of GIVE.

Abstract: Aiming at the detail rendering in volume data, a new volume illumination model, called Composed Scattering Model (CSM), is presented. In order to enhance different details in volume data, scattering intensity is decomposed into volume scattering intensity and surface scattering intensity with different weight functions. According to the Gauss probability distribution of gray and gradient of data, we propose an accurate method to detect the materials in a voxel, called composed segmentation. In addition, we discuss the principle of constructing these weight functions based on the operators defined in composed segmentation. CSM can generate images containing more details than most popular volume rendering models. This model has been applied to the direct volume rendering of 3D data sets obtained by CT and MRI. The resultant images show not only rich details but also clear boundary surfaces. CSM is demonstrated as an accurate volume rendering model suited for detail enhancement in volume data sets.