{"title":"Automatic shape morphing for Chinese characters","authors":"Z. Lian, Jianguo Xiao","doi":"10.1145/2407746.2407748","DOIUrl":"https://doi.org/10.1145/2407746.2407748","url":null,"abstract":"How to automatically implement shape morphing for Chinese characters represented in different styles is a challenging task. In this paper, we propose a novel method to solve this problem. Specifically, we first generate the shape template, which includes a skeleton, strokes, key points, and connection triangles, for every character in a standard Chinese font (i.e., Kaiti) library. Then, we decompose two given Chinese characters into strokes to establish an accurate correspondence between them by applying the Coherent Point Drift (CPD) algorithm to achieve non-rigid point set registration between each character and the corresponding template. Finally, we construct an isomorphic triangulation for the source and target character shapes, and then apply as-rigid-as-possible shape interpolation on these two triangle meshes. Experimental results demonstrate the effectiveness of our method.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"18 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":"116785401","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}
Junhui Hou, Lap-Pui Chau, Ying He, D. T. P. Quynh, N. Magnenat-Thalmann
{"title":"Dynamic 3-D facial compression using low rank and sparse decomposition","authors":"Junhui Hou, Lap-Pui Chau, Ying He, D. T. P. Quynh, N. Magnenat-Thalmann","doi":"10.1145/2407746.2407768","DOIUrl":"https://doi.org/10.1145/2407746.2407768","url":null,"abstract":"In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique. Then, low rank and sparse decomposition is applied to each dimension (i.e., X, Y and Z, respectively) before the H.264/AVC encoder is employed to separately encode each dimension instead of encoding them as a whole. Experimental results show that the averaged 3-4 dB gain is achieved by the proposed scheme compared with existing algorithms.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"14 35 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":"132556358","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":"Edge-preserving image decomposition using L1 fidelity with L0 gradient","authors":"C. Shen, Feng-Ju Chang, Y. Hung, S. Pei","doi":"10.1145/2407746.2407752","DOIUrl":"https://doi.org/10.1145/2407746.2407752","url":null,"abstract":"We present an image decomposition method using L1 fidelity term with L0 norm of gradient to decompose an image into base layer and detail layer. Generally, the L1 fidelity should be preferable to the L2 norm when the erroneous measurements exist. It is also reported that the L0 norm of gradient is a better prior term than total variation and the L2 norm of gradient. Therefore, we combine these two benefits to obtain our base layer by adopting our method using L1 fidelity and L0 gradient. Our image decomposition method can be regarded as the fundamental tool to generate multiple image editing applications, such as image denoising, edge detection, detail enhancement, cartoon JPEG artifact removal, local tone mapping, and contrast enhancement under low backlight condition. Experimental results show that our proposed method is promising as compared to the existing methods.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"62 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":"132801339","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}
A. Khosla, Jianxiong Xiao, Phillip Isola, A. Torralba, A. Oliva
{"title":"Image memorability and visual inception","authors":"A. Khosla, Jianxiong Xiao, Phillip Isola, A. Torralba, A. Oliva","doi":"10.1145/2407746.2407781","DOIUrl":"https://doi.org/10.1145/2407746.2407781","url":null,"abstract":"When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. However, not all images are equal in memory; some stitch to our minds, while others are forgotten. In this paper we discuss the notion of image memorability and the elements that make it memorable. Our recent works have shown that image memorability is a stable and intrinsic property of images that is shared across different viewers. Given that this is the case, we discuss the possibility of modifying the memorability of images by identifying the memorability of image regions. Further, we introduce and provide evidence for the phenomenon of visual inception: can we make people believe they have seen an image they have not?","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"8 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":"127713141","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":"Adaptive dynamics with hybrid response","authors":"Nam Nguyeny, Raul Arista, C. Liu, V. Zordan","doi":"10.1145/2407746.2407751","DOIUrl":"https://doi.org/10.1145/2407746.2407751","url":null,"abstract":"This paper describes a hybrid technique to produce physically plausible response for animated character. The approach includes the automatic, adaptive selection of the dynamic articulation necessary for local-body responses based on the changing conditions of the character. This method is combined with a whole-body reaction to disturbances which is computed and controlled separately. Combined, the resulting response effects the entire body as well as the local area of a disturbance without the need for an explicit full-body controller and the response computed is both deliberate (controlled) and passive (uncontrolled). The results showcase a variety of scenarios including fast and sustained contact.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"12 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":"127488176","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}
Etan Kissling, Kenny Mitchell, Thomas Oskam, M. Gross
{"title":"Efficient rasterization for edge-based 3d object tracking on mobile devices","authors":"Etan Kissling, Kenny Mitchell, Thomas Oskam, M. Gross","doi":"10.1145/2407746.2407758","DOIUrl":"https://doi.org/10.1145/2407746.2407758","url":null,"abstract":"Augmented reality applications on hand-held devices suffer from the limited available processing power. While methods to detect the location of artificially textured markers within the scene are commonly used, geometric properties of three-dimensional objects are rarely exploited for object tracking. In order to track such geometry efficiently on mobile devices, existing methods must be adapted. By focusing on key behaviors of edge-based models, we present a sparse depth buffer structure to provide an efficient rasterization method. This allows the tracking algorithm to run on a single CPU core of a current-generation hand-held device, while requiring only minimal support from the GPU.","PeriodicalId":201780,"journal":{"name":"SIGGRAPH Asia 2012 Technical Briefs","volume":"11 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":"126868202","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}