Takanori Nishino, Kei Iwasaki, Y. Dobashi, T. Nishita
{"title":"Visual simulation of freezing ice with air bubbles","authors":"Takanori Nishino, Kei Iwasaki, Y. Dobashi, T. Nishita","doi":"10.1145/2407746.2407747","DOIUrl":"https://doi.org/10.1145/2407746.2407747","url":null,"abstract":"Ice often contains small air bubbles that are dissolved air exhausted from water-ice interface. Depicting these air bubbles with various sizes enhances the realism of ice. This paper proposes a fast simulation method of freezing ice taking into account air bubbles. Our method introduces a physically-based calculation method of the sizes of air bubbles based on the freezing velocity and pressure. In contrast to the previous method, our method can represent numerous small bubbles that cannot be represented by using the resolutions of simulation grids. The computations of heat transfer, tracking of water-ice interface, and generation of bubbles are accelerated by implementing our method using CUDA. Our method achieves the freezing simulation and bubble generation at interactive frame-rates.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121253216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using text N-grams for model suggestions in 3D scenes","authors":"L. Lam, Sharon Lin, P. Hanrahan","doi":"10.1145/2407746.2407776","DOIUrl":"https://doi.org/10.1145/2407746.2407776","url":null,"abstract":"Creating 3D scenes requires artistic skill and is time-consuming. A key challenge is finding novel models to place in a partial scene. We present a new algorithm to propose relevant models by leveraging text data. Our algorithm takes a partially completed 3D scene as input and a user-specified region of interest. It then suggests additional models according to the point-wise mutual information between the labels of nearby models in the scene and the labels of models in the database. We show that our text-based system suggests more models that result in model arrangements not observed in the training corpus, compared to a Graph Kernel system that trains on 3D scene data. Furthermore, combining the Graph Kernel system with our new system increases the number of unobserved model arrangements for the Graph Kernel, with higher precision according to human evaluators.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126140783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Pirk, Michael F. Cohen, O. Deussen, M. Uyttendaele, J. Kopf
{"title":"Video enhanced gigapixel panoramas","authors":"S. Pirk, Michael F. Cohen, O. Deussen, M. Uyttendaele, J. Kopf","doi":"10.1145/2407746.2407753","DOIUrl":"https://doi.org/10.1145/2407746.2407753","url":null,"abstract":"We present a method for embedding video clips within gigapixel scale imagery. The combination of high-resolution imagery and video enables users to pan and zoom across the gigapixel panorama to explore complex scenes with motion. The sparsity of the video content within the gigapixel context introduces several challenges which we overcome by optimizing the traversal of the scene coupled with appropriate playback of the embedded video. We also discuss aligning the video clips both geometrically and photometrically to reduce visible seams between the dynamic and static content. Embedding video in large scale panoramas fills a gap between static gigapixel images and video footage and thus presents a new interactive medium.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133544852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhenglong Zhou, Bo Shu, Shaojie Zhuo, Xiaoming Deng, P. Tan, Stephen Lin
{"title":"Image-based clothes animation for virtual fitting","authors":"Zhenglong Zhou, Bo Shu, Shaojie Zhuo, Xiaoming Deng, P. Tan, Stephen Lin","doi":"10.1145/2407746.2407779","DOIUrl":"https://doi.org/10.1145/2407746.2407779","url":null,"abstract":"We propose an image-based approach for virtual clothes fitting, in which a user moves freely in front of a virtual mirror (i.e., video screen) that displays the user wearing a superimposed virtual garment. The motions and deformations of the virtual garment are synthesized by tracking the user's skeleton and utilizing corresponding video clips of the actual garment worn by a model. Our system overcomes challenges in generating a convincing garment animation. With our technique, we developed a real-time system using a Microsoft Kinect camera that demonstrates effective clothes fitting results with a variety of garment types.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131908040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimized anaglyph colorization","authors":"H. Lin, Chih-Lin Zheng, Yu-Hsun Lin, M. Ouhyoung","doi":"10.1145/2407746.2407755","DOIUrl":"https://doi.org/10.1145/2407746.2407755","url":null,"abstract":"The anaglyph image, primarily used for red-cyan eyeglasses, has the following flaws: it only reproduces partial colors, often brings retinal rivalry and ghosting to viewers. In this paper, we propose a method for anaglyph image recoloring to enhance the color perception and reduce the visual fatigue. When an anaglyph image is given, a corresponding stereo pair can be derived. The goal of this paper is to restore lost colors of the stereo pair and thus convert the anaglyph into full-color 3D contents. Our main idea is to transfer existing information of the images to each other and we formulate this problem as a labeling problem. We compare our results with the input anaglyph and the results of a naïve color transfer method. Our user study shows that the results from our method improve the viewing experience for anaglyph contents at 95% confidence level, and have less artifacts compared to a naïve color transfer method.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124320827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The pipeline of facial animation fast forward: the NMA example","authors":"Rh Shih, Jackson Lee, Jeff Lin, Richard Chuang","doi":"10.1145/2407746.2407771","DOIUrl":"https://doi.org/10.1145/2407746.2407771","url":null,"abstract":"In the domain of computer graphic, to achieve facial animation looks like real human performance without any bias is always the holy grail of related research academy and industry[Ma 2008]. Next Media Animation (NMA) as the Asia's leading animation studio is famous for applying the fast production pipeline to generate news animation and cartoon episodes. We has developed a unique pipeline, following the scenario to assemble models from our own data base with mocap data to render out news story for worldwide broadcasting in two hours. However, for the high-end quality, to develop a practical and fast pipeline for merging facial animation into NMA current news pipeline without any additional time request has become an issue of our Media Lab R&D team.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116129209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Region matching with proxy ellipses for coloring hand-drawn animations","authors":"Yoshihiro Kanamori","doi":"10.1145/2407746.2407750","DOIUrl":"https://doi.org/10.1145/2407746.2407750","url":null,"abstract":"Hand-drawn animations are fascinating due to their expressiveness. In the production pipeline, manual coloring of line drawings is tedious and labor-intensive. We propose a method for accelerating the coloring step by matching corresponding regions in successive frames and propagating the same color to the regions. We derive a matching cost between two regions based on ellipses that approximate the orientations, scales and positions of regions. Such ellipses are insensitive to frequent changes of the region-contour shape un-like contour-based features used in previous methods. Our method finds an optimal matching that minimizes the total matching cost quickly. We demonstrate the speed and the matching accuracy of our method with comparisons.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121649822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A global algorithm to compute defect-tolerant geodesic distance","authors":"Shiqing Xin, D. T. P. Quynh, Xiang Ying, Ying He","doi":"10.1145/2407746.2407769","DOIUrl":"https://doi.org/10.1145/2407746.2407769","url":null,"abstract":"Computing geodesic distance on surfaces plays a critical role in digital geometry processing. However, due to its locally shortest nature, geodesic distance is highly sensitive to local geometrical and topological changes, diminishing its applications to real-world models which may contain various types of defects. This paper presents a new algorithm to compute defect-tolerant geodesic distance on broken meshes. In contrast to the existing approaches which compute the distance from source to destinations in a single Dijkstra-like sweep, our method proceeds in an iterative and global manner. Thanks to its global nature, the resulting distance is tolerant to some defects (e.g. holes, gaps, shortcuts), insensitive to mesh tessellation/resolution, and robust to noise, which provides a meaningful approximation of geodesics on broken meshes.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122468481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time contrast preserving decolorization","authors":"Cewu Lu, Li Xu, Jiaya Jia","doi":"10.1145/2407746.2407780","DOIUrl":"https://doi.org/10.1145/2407746.2407780","url":null,"abstract":"Decolorization -- the process to transform a color image to a grayscale one -- is a basic tool in digital printing, stylized black-and-white photography, and in many single channel image and video processing applications. While recent research focuses on retaining meaningful visual features and color contrast, less attention has been paid to the complexity issue of the conversion. Consequently, the resulting decolorization methods could be orders of magnitude slower than simple procedures, e.g., Matlab built-in rgb2gray function, which could hamper them from being used practically. In this paper, we propose a very fast and yet effective decolorization approach. The effectiveness of the method is borne out by a new quantitative metric as well as qualitative comparisons with state-of-the-art methods.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115575038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mei-Yun Chen, Yung-Hsiang Yang, Chia Ju Ho, Shih-Han Wang, Shane-Ming Liu, Eugene Chang, C. Yeh, M. Ouhyoung
{"title":"Automatic Chinese food identification and quantity estimation","authors":"Mei-Yun Chen, Yung-Hsiang Yang, Chia Ju Ho, Shih-Han Wang, Shane-Ming Liu, Eugene Chang, C. Yeh, M. Ouhyoung","doi":"10.1145/2407746.2407775","DOIUrl":"https://doi.org/10.1145/2407746.2407775","url":null,"abstract":"Computer-aided food identification and quantity estimation have caught more attention in recent years because of the growing concern of our health. The identification problem is usually defined as an image categorization or classification problem and several researches have been proposed. In this paper, we address the issues of feature descriptors in the food identification problem and introduce a preliminary approach for the quantity estimation using depth information. Sparse coding is utilized in the SIFT and Local binary pattern feature descriptors, and these features combined with gabor and color features are used to represent food items. A multi-label SVM classifier is trained for each feature, and these classifiers are combined with multi-class Adaboost algorithm. For evaluation, 50 categories of worldwide food are used, and each category contains 100 photographs from different sources, such as manually taken or from Internet web albums. An overall accuracy of 68.3% is achieved, and success at top-N candidates achieved 80.6%, 84.8%, and 90.9% accuracy accordingly when N equals 2, 3, and 5, thus making mobile application practical. The experimental results show that the proposed methods greatly improve the performance of original SIFT and LBP feature descriptors. On the other hand, for quantity estimation using depth information, a straight forward method is proposed for certain food, while transparent food ingredients such as pure water and cooked rice are temporarily excluded.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"110 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121739285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}