2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images最新文献

A New Hierarchical Decomposition Applied to Object Segmentation in Image Sequences: The Uniform Decomposition 一种新的用于图像序列目标分割的层次分解方法:均匀分解

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.29

F. C. Flores, R. Lotufo

引用次数: 5

Topology Aware Vector Field Denoising 拓扑感知向量场去噪

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.22

Renata Nascimento, J. Paixão, H. Lopes, T. Lewiner

引用次数: 4

Partial Matching Using Set Exclusion Criteria: Applied to Livestock Brand Retrieval 基于集合排除标准的部分匹配:应用于家畜品牌检索

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.32

Waldemar Villamayor-Venialbo, H. Legal-Ayala, E. Justino, J. Facon

引用次数: 1

Interactive Simulation and Visualization of Fluids with Surface Raycasting 基于表面光线投射的流体交互仿真与可视化

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.27

Renan Teston Inácio, Tiago Nobrega, Diego D. B. Carvalho, A. V. Wangenheim

引用次数: 3

3D Linear Facial Animation Based on Real Data 基于真实数据的三维线性面部动画

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.44

Andréa Britto Mattos, J. Mena-Chalco, R. M. C. Junior, L. Velho

{"title":"3D Linear Facial Animation Based on Real Data","authors":"Andréa Britto Mattos, J. Mena-Chalco, R. M. C. Junior, L. Velho","doi":"10.1109/SIBGRAPI.2010.44","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2010.44","url":null,"abstract":"In this paper we introduce a Facial Animation system using real three-dimensional models of people, acquired by a 3D scanner. We consider a dataset composed by models displaying different facial expressions and a linear interpolation technique is used to produce a smooth transition between them. One-to-one correspondences between the meshes of each facial expression are required in order to apply the interpolation process. Instead of focusing in the computation of dense correspondence, some points are selected and a triangulation is defined, being refined by consecutive subdivisions, that compute the matchings of intermediate points. We are able to animate any model of the dataset, given its texture information for the neutral face and the geometry information for all the expressions along with the neutral face. This is made by computing matrices with the variations of every vertex when changing from the neutral face to the other expressions. The knowledge of the matrices obtained in this process makes it possible to animate other models given only the texture and geometry information of the neutral face. Furthermore, the system uses 3D reconstructed models, being capable of generating a three-dimensional facial animation from a single 2D image of a person. Also, as an extension of the system, we use artificial models that contain expressions of visemes, that are not part of the expressions of the dataset, and their displacements are applied to the real models. This allows these models to be given as input to a speech synthesis application in which the face is able to speak phrases typed by the user. Finally, we generate an average face and increase the displacements between a subject from the dataset and the average face, creating, automatically, a caricature of the subject.","PeriodicalId":320252,"journal":{"name":"2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117209778","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}

引用次数: 7

Eyes and Eyebrows Detection for Performance Driven Animation 性能驱动动画的眼睛和眉毛检测

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.11

J. L. Moreira, Adriana Braun, S. Musse

引用次数: 13

Predictive Lazy Amplification: Synthesis and Rendering of Massive Procedural Scenes in Real Time 预测延迟放大:实时合成和渲染大量程序场景

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.43

Carlúcio Cordeiro, L. Chaimowicz

引用次数: 3

On Generalized Differences for Biospeckle Image Analysis 生物散斑图像分析的广义差分

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.36

A. Saúde, F. S. D. Menezes, Patrícia L. S. Freitas, G. Rabelo, R. Braga

{"title":"On Generalized Differences for Biospeckle Image Analysis","authors":"A. Saúde, F. S. D. Menezes, Patrícia L. S. Freitas, G. Rabelo, R. Braga","doi":"10.1109/SIBGRAPI.2010.36","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2010.36","url":null,"abstract":"Biospeckle is a technique whose purpose is to observe and study the underlying activity of some material. The technique has its roots on optical physics, and its first step is an image acquisition process that produces a video sequence whose characteristics allow researchers to have an interpretation of the activity of the observed material by an analysis of the video content. The recent literature on this subject presents several different measurements for analyzing the video sequence. One of the most popular measurement is the Generalized Difference (GD). The computation of the GD has an asymptotic complexity of O(n2). In this paper we propose: i) an alternative O(n) algorithm for the computation of the GD, and ii) an alternative measurement, that we call GD*. We discuss the qualitative similarities between the GD and the GD*. We conclude that the GD* is an alternative generalized difference measurement, and thus it can replace the GD in many applications. We show that the GD* is a function of the variance, and it can be computed in O(n). Finally, if the GD itself is desired as measurement, it can now be computed in O(n) by the novel algorithm presented in this paper.","PeriodicalId":320252,"journal":{"name":"2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images","volume":"789 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116416257","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}

引用次数: 10

Efficient Approximate Visibility of Point Sets on the GPU GPU上点集的高效近似可见性

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.40

Denison L. M. Tavares, J. Comba

引用次数: 3

Using Acceleration Data from Smartphones to Interact with 3D Medical Data 使用智能手机的加速度数据与3D医疗数据进行交互

2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images Pub Date : 2010-08-30 DOI: 10.1109/SIBGRAPI.2010.52

M. Souza, Diego D. B. Carvalho, Peter Barth, J. V. Ramos, E. Comunello, A. V. Wangenheim

引用次数: 13