In this paper, we report on a parallel freeviewpoint video synthesis algorithm that can efficiently reconstruct a high-quality 3D scene representation of sports scenes. The proposed method focuses on a scene that is captured by multiple synchronized cameras featuring wide-baselines. The following strategies are introduced to accelerate the production of a free-viewpoint video taking the improvement of visual quality into account: (1) a sparse point cloud is reconstructed using a volumetric visual hull approach, and an exact 3D ROI is found for each object using an efficient connected components labeling algorithm. Next, the reconstruction of a dense point cloud is accelerated by implementing visual hull only in the ROIs; (2) an accurate polyhedral surface mesh is built by estimating the exact intersections between grid cells and the visual hull; (3) the appearance of the reconstructed presentation is reproduced in a view-dependent manner that respectively renders the non-occluded and occluded region with the nearest camera and its neighboring cameras. The production for volleyball and judo sequences demonstrates the effectiveness of our method in terms of both execution time and visual quality.
This paper presents a scheme which utilizes comments given to images on an image-sharing site in order to obtain an appropriate image for insertion into poem-like weblogs (blogs) as a way to represent their atmosphere (impression). The result shows that utilizing comments is effective. To achieve this purpose, there are two issues: how impression words are extracted from blogs and how images representing the impression words are obtained. Assuming that it is important to obtain images representing the impression words, this paper focuses on only the latter issue. We hypothesize that comments and tags extracted from an image-sharing site can be adequate for obtaining images corresponding to impression words at low cost. In particular, utilizing comments can be more appropriate for the image search with impression words than utilizing tags because the impression words are often used in comments. Therefore, we propose a scheme which utilizes comments to obtain appropriate images. In order to investigate the effectiveness of utilizing comments, conformance between impression words and the images was evaluated. The rating for conformance is 3.5 on a scale of 1 to 5 when utilizing comments, which is 0.6 higher than when utilizing tags.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.