Abstract:This special issue on computer graphics consists of four papers addressing respectively the elds of image morphing, video processing, document visualization andGPU algorithms. Image morphing is a classic technique widely used for special e ects in entertainment industry. The rst paper by Tomohisa Manabe et al. proposes a method for generating a sequence of images with smooth change of illumination between two input images under di erent lighting conditions. It adopts isoluminance curves as a feature primitive. Transformed luminance distributions are generated from the warped isoluminance curves. In the second paper, Chunxia Xiao et al. present a fast gradient domain based framework for video compositing. Rather than the conventional approaches which performs Poisson image editing in the gradient-domain pixel by pixel, the new framework conducts video compositing by incorporating an octree data structure, requesting greatly reduced computational time and memory space. Discovering concepts from vast amount of text is an important but hard explorative task. The third paper by Qian You et al. proposes the iterative visual clustering (IVC), a noval visual text analytical model. IVC has a formal on-line learning model which learns users' preference iteratively. With the engagement of domain knowledge, it can achieve insightful concepts with interesting patterns. Graphics processing units (GPUs) have an SIMD architecture and have found wide applications in various elds. The last paper by Baoyuan Wang and Yizhou Yu investigates e cient GPU-based data cubing which is an expensive operation well suited for SIMD parallel e ective methods. The proposed algorithms can achieve more than one order of magnitude speedup when compared with their sequential counterparts on a single CPU. Finally, I would like to thank all the authors of the above four papers for their contribution to this special issue and appreciate the excellent work by all the reviewers.

Abstract:The paper proposes a method for generating a sequence of images with smooth change of illumination from two input images with different lighting conditions. The idea of the proposed method is based on image morphing. While conventional image morphing changes object shapes between two input images, here we focus on changing the illumination between two images. The proposed method uses isoluminance curves as a feature primitive. Isoluminance curves acquired from images are warped based on the correspondence of the curves between two images, and transformed luminance distributions are generated from the warped isoluminance curves. The proposed method called "illumination morphing" is able to generate smooth transition of luminance between two color images. The method does not need even the information about the light sources and 3D object models. The proposed method is a promising technique for many applications requiring a scene with variety of lighting effects, such as movies, TV games, and so on.

Abstract:We present a fast gradient domain video processing using hierarchical data structure which subdivides the processing region into an octree data. It is hard to handle large video processing by solving a 3D Poisson equation, as the derived linear system is usually large. Solving the system requires large memory space and long computational time, which makes it intractable on a standard computer. To address the scalability problem, rather than processing the video in the gradient-domain pixel by pixel, we perform the video processing in a reduced space using octree data structure, which significantly reduces the variables. We show that the proposed octree approach is efficient in both seamless and mixing gradient-domain video processing. The method enables to perform video processing in greatly reduced computational time and memory space, while receiving visually identical results with that computed from the full solution.

Abstract:Discovering concepts from vast amount of text is is an important but hard explorative task. A common approach is to identify meaningful keyword clusters with interesting temporal distributive trends from unstructured text. However, usually lacking clearly de ned objective functions, users' domain knowledge and interactions need to be feed back and to drive the clustering process. Therefore we propose the iterative visual clustering (IVC), a noval visual text analytical model. It uses di erent types of visualizations to help users cluster keywords interactively, as well as uses graphics to suggest good clustering options. The most distinctive di erence between IVC and traditional text analytical tools is, IVC has a formal on-line learning model which learns users' preference iteratively: during iterations, IVC transforms users' interactions into model training input, and then visualizes the output for more users interactions. We apply IVC as a visual text mining framework to extract concepts from nursing narratives. With the engagement of domain knowledge, IVC has achieved insightful concepts with interesting patterns.

Abstract:Graphics processing units (GPUs) have an SIMD architecture and have been widely used recently as powerful general-purpose co-processors for the CPU. In this paper, we investigate efficient GPU-based data cubing because the most frequent operation in data cube computation is aggregation, which is an expensive operation well suited for SIMD parallel processors. H-tree is a hyper-linked tree structure used in both top-k H-cubing and the stream cube. Fast H-tree construction, update and real-time query response are crucial in many OLAP applications. We design highly efficient GPU-based parallel algorithms for these H-tree based data cube operations. This has been made possible by taking effective methods, such as parallel primitives for segmented data and efficient memory access patterns, to achieve load balance on the GPU while hiding memory access latency. As a result, our GPU algorithms can often achieve more than an order of magnitude speedup when compared with their sequential counterparts on a single CPU. To the best of our knowledge, this is the first attempt to develop parallel data cubing algorithms on graphics processors.

Abstract:With the exploration of video data, it is difficult for people to navigate freely and make full use of amount of video data efficiently in order to get useful information or knowledge with an aim to fulfill special tasks such as visual analysis. In this paper, we propose a novel sketch based interface which is called StroyMap for video content representation and navigation under the guideline of distributed cognition. Instead of emphasizing on details, the sketches visualized the essential content of video effectively. In order to meet different requirement for video exploration tasks, StoryMap provides users a variety of navigation ways, such as path redirection, map tagging, zoom in and zoom out. During the whole interaction process, the system will collect user's operation list, construct user model as a guide to understand interaction between people and computer. Experimental evaluation results show that StoryMap plays more effiective role in conveying and navigating video content compared with existing methods.