发布求助
文献互助 智能选刊 最新文献

2008 XXI Brazilian Symposium on Computer Graphics and Image Processing最新文献

筛选
英文 中文
A Parallel Multi-view Rendering Architecture 并行多视图渲染体系结构
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.41
W. Lages, Carlúcio Cordeiro, D. Guedes
{"title":"A Parallel Multi-view Rendering Architecture","authors":"W. Lages, Carlúcio Cordeiro, D. Guedes","doi":"10.1109/SIBGRAPI.2008.41","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.41","url":null,"abstract":"We present an architecture for rendering multiple views efficiently on a cluster of GPUs. The original scene is sampled by virtual cameras which are used later to reconstruct the desired views. We show that this image-based approach can be very scalable and support rendering at interactive rates.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131166501","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: 4
Simulation and Rendering of Opus Palladium 3D Mosaics Opus Palladium 3D马赛克的仿真与渲染
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.12
V. A. D. Passos, M. Walter
{"title":"Simulation and Rendering of Opus Palladium 3D Mosaics","authors":"V. A. D. Passos, M. Walter","doi":"10.1109/SIBGRAPI.2008.12","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.12","url":null,"abstract":"Mosaic sculptures are a form of art where the sculpture is made from a collection of individual elements called tiles which are distributed over the surface of a given 3D shape. To add expressiveness, artists distribute the tiles following a high-level design over the shape, in order to emphasize some features. In the method known by mosaicists as opus palladium, or simply \"crazy paving\", tiles with irregular shapes are used, improving the expressivity of the final result. In this work, we present a method to simulate this kind of 3D mosaic by representing tiles as Voronoi polygons computed from a distribution of points on the surface of the 3D object. Previous work on this topic have used only square-shaped tiles. Special mosaic-like effects are obtained with the help from texture maps, which control the high-level design of the tiles.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130949617","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: 3
Shape Aware Deformation Using a Skeleton-Guided Scheme 使用骨架引导方案的形状感知变形
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.37
Álvaro Cuno, Claudio Esperança, Antonio A. F. Oliveira
{"title":"Shape Aware Deformation Using a Skeleton-Guided Scheme","authors":"Álvaro Cuno, Claudio Esperança, Antonio A. F. Oliveira","doi":"10.1109/SIBGRAPI.2008.37","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.37","url":null,"abstract":"This work presents a method for deforming meshes in a shape-sensible way using moving least squares (MLS) optimization.It is explained how an approach for space deformation can be transformed into a skeleton-guided deformation scheme, where more sensitivity to the mesh geometry is achieved. Given a mesh and its skeleton, for each joint a minimization problem is solved subject to positional constraints given by the user. The mesh geometry is then modified by blending optimal transformations computed at skeleton joints associated with each vertex of the mesh. Additionally, it is shown how a small reformulation of the MLS scheme makes it possible to affect the bending behavior of the deformation.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115349088","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: 1
VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation VSUMM:一种自动视频摘要与定量评价方法
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.31
S. Avila, A. D. Luz, A. Araújo, M. Cord
{"title":"VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation","authors":"S. Avila, A. D. Luz, A. Araújo, M. Cord","doi":"10.1109/SIBGRAPI.2008.31","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.31","url":null,"abstract":"In this paper, we propose an approach for video summarization (VSUMM). The video summaries are generated based on visual features. A factorial experiment is designed to analyze the relative impact of the attributes. We demonstrate the validity of the VSUMM approach by testing it on a collection of videos from Open Video Project. We provide a comparison among results of the proposed summarization technique with Open Video storyboard. A subjective evaluation showed that the summaries are produced with good quality.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117200878","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: 48
Projective Estimators for Point/Tangent Representations of Planar Curves 平面曲线点/切线表示的投影估计
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.6
T. Lewiner, M. Craizer
{"title":"Projective Estimators for Point/Tangent Representations of Planar Curves","authors":"T. Lewiner, M. Craizer","doi":"10.1109/SIBGRAPI.2008.6","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.6","url":null,"abstract":"Recognizing shapes in multiview imaging is still a challenging task, which usually relies on geometrical invariants estimations. However, very few geometric estimators that are projective invariant have been devised.This paper proposes projective length and projective curvature estimators for plane curves, when the curves are represented by points together with their tangent directions. In this context, the estimations can be performed with only the four point-tangent samples for the projective length and five for the projective curvature.The proposed length estimator is based on affine estimators and is proved to be convergent. The curvature estimator relies on the length to fit logarithmic spirals to the point-tangent samples. It is projective invariant and experiments indicate its convergence. Preliminary results using both estimators together are promising, although the estimators' lack of robustness would require additional work for noisy cases.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124014233","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: 4
PCA-Based 3D Face Photography 基于pca的3D人脸摄影
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.40
J. Mena-Chalco, Ives Macêdo, L. Velho, R. M. C. Junior
{"title":"PCA-Based 3D Face Photography","authors":"J. Mena-Chalco, Ives Macêdo, L. Velho, R. M. C. Junior","doi":"10.1109/SIBGRAPI.2008.40","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.40","url":null,"abstract":"This paper presents a 3D face photography system based on a small set of training facial range images. The training set is composed by 2D texture and 3D range images (i.e. geometry) of a single subject with different facial expressions. The basic idea behind the method is to create texture and geometry spaces based on the training set and transformations to go from one space to the other. The main goal of the proposed approach is to obtain a geometry representation of a given face provided as a texture image, which undergoes a series of transformations through the texture and geometry spaces. Facial feature points are obtained by an active shape model (ASM) extracted from the 2D gray-level images. PCA then is used to represent the face dataset, thus defining an orthonormal basis of texture and range data. An input face is given by a gray-level face image to which the ASM is matched. The extracted ASM is fed to the PCA basis representation and a 3D version of the 2D input image is built. The experimental results on static images and video sequences using seven samples as training dataset show rapid reconstructed 3D faces which maintain spatial coherence similar to the human perception, thus corroborating the efficiency of our approach.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122896348","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: 8
High Quality Image Reconstruction of Point Models 点模型的高质量图像重建
2008 XXI Brazilian Symposium on Computer Graphics and Image Processing Pub Date : 2008-10-12 DOI: 10.1109/SIBGRAPI.2008.29
R. Marroquim, Antonio A. F. Oliveira, P. R. Cavalcanti
{"title":"High Quality Image Reconstruction of Point Models","authors":"R. Marroquim, Antonio A. F. Oliveira, P. R. Cavalcanti","doi":"10.1109/SIBGRAPI.2008.29","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2008.29","url":null,"abstract":"The parallel and discrete nature of many image-based techniques, such as interpolation methods, are highly suitable for GPU implementations. An important advantage is their bounded complexity by the screen resolution as opposed to the data size. Consequently, the direct surface reconstruction of points using image-based methods is an attractive solution to interactively render large data-sets. In this paper, we propose a novel approach that raises the robustness and quality standards of previous related works. The algorithm achieves quality equivalent to surface splatting techniques, while maintaining high performance rates compatible with previous image-based methods. A hierarchical pixel structure is employed to render the projected samples efficiently with minimum artifacts. One of the main advantages of the method is the independency from the number of samples during the surface reconstruction. Furthermore, no extra object space data structure is needed, making the approach also memory efficient.","PeriodicalId":330622,"journal":{"name":"2008 XXI Brazilian Symposium on Computer Graphics and Image Processing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115926273","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: 1
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信