Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240859
S. Lee, R. Nevatia
Modeling and visualization of city scenes is important for many applications including entertainment and urban mission planning. Models covering wide areas can be efficiently constructed from aerial images. However, only roof details are visible from aerial views and ground views are needed to provide details of the building facades for high quality fly-through visualization or simulation applications. Different data sources provide different levels of necessary detail knowledge. We need a method that integrates the various levels of data. We propose a hierarchical representation of 3D building models for urban areas that integrates different data sources including aerial and ground view images. Each data source gives us different details and each level of the model has its own application as well. Through the hierarchical representation of 3D building models, large area site modeling can be done efficiently and cost-effectively. This proposal suggests efficient approaches for acquiring each level model and demonstrates some results of each level including the integration results.
{"title":"Interactive 3D building modeling using a hierarchical representation","authors":"S. Lee, R. Nevatia","doi":"10.1109/HLK.2003.1240859","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240859","url":null,"abstract":"Modeling and visualization of city scenes is important for many applications including entertainment and urban mission planning. Models covering wide areas can be efficiently constructed from aerial images. However, only roof details are visible from aerial views and ground views are needed to provide details of the building facades for high quality fly-through visualization or simulation applications. Different data sources provide different levels of necessary detail knowledge. We need a method that integrates the various levels of data. We propose a hierarchical representation of 3D building models for urban areas that integrates different data sources including aerial and ground view images. Each data source gives us different details and each level of the model has its own application as well. Through the hierarchical representation of 3D building models, large area site modeling can be done efficiently and cost-effectively. This proposal suggests efficient approaches for acquiring each level model and demonstrates some results of each level including the integration results.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128908837","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240853
C. Basso, T. Vetter, V. Blanz
Three-dimensional morphable models of objects classes are a powerful tool in modeling, animation and recognition. We introduce the new concept of regularized 3D morphable models, along with an iterative learning algorithm, by adding in the statistical model a noise/regularization term which is estimated from the examples set. With regularized 3D morphable models we are able to handle missing information, as it often occurs with data obtained by 3D acquisition systems; additionally, the new models are less complex than, but as powerful as the non-regularized ones. We present the results obtained for a set of 3D face models and a comparison with the new ones obtained by a traditional morphable model on the same data set.
{"title":"Regularized 3D morphable models","authors":"C. Basso, T. Vetter, V. Blanz","doi":"10.1109/HLK.2003.1240853","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240853","url":null,"abstract":"Three-dimensional morphable models of objects classes are a powerful tool in modeling, animation and recognition. We introduce the new concept of regularized 3D morphable models, along with an iterative learning algorithm, by adding in the statistical model a noise/regularization term which is estimated from the examples set. With regularized 3D morphable models we are able to handle missing information, as it often occurs with data obtained by 3D acquisition systems; additionally, the new models are less complex than, but as powerful as the non-regularized ones. We present the results obtained for a set of 3D face models and a comparison with the new ones obtained by a traditional morphable model on the same data set.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122437212","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240858
Kongbin Kang, Jean-Philippe Tarel, D. Cooper
A theory and low computational cost linear algorithm is presented for estimating algebraic surfaces of second degree for representing an object in 3D, based on fitting in the dual space (space of tangent planes) computed from images taken by a calibrated camera in a number of positions. The approach and algorithm are designed to handle implicit quadric surfaces, which are regular or singular, in a uniform way without distinguishing the two cases. A significance of these quadric surface estimation results is, as illustrated in the paper, the estimation of complex 3D free form shapes in a computationally simple way in terms of quadric patches. The paper explains how singular quadrics cause instabilities in the 3D surface fitting and representation, and presents regularization, based on this understanding, to produce accurate stable surface representations.
{"title":"A unified linear fitting approach for singular and nonsingular 3D quadrics from occluding contours","authors":"Kongbin Kang, Jean-Philippe Tarel, D. Cooper","doi":"10.1109/HLK.2003.1240858","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240858","url":null,"abstract":"A theory and low computational cost linear algorithm is presented for estimating algebraic surfaces of second degree for representing an object in 3D, based on fitting in the dual space (space of tangent planes) computed from images taken by a calibrated camera in a number of positions. The approach and algorithm are designed to handle implicit quadric surfaces, which are regular or singular, in a uniform way without distinguishing the two cases. A significance of these quadric surface estimation results is, as illustrated in the paper, the estimation of complex 3D free form shapes in a computationally simple way in terms of quadric patches. The paper explains how singular quadrics cause instabilities in the 3D surface fitting and representation, and presents regularization, based on this understanding, to produce accurate stable surface representations.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123953772","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240857
M. Kaess, F. Dellaert
In some applications objects are known to have non-smooth or "jagged" edges, which are not well approximated by smooth curves. We use subdivision curves as a simple but flexible curve representation, which allows tagging corners to model non-smooth features along otherwise smooth curves. A Markov chain Monte Carlo approach yields an approximate posterior distribution over tags, while Rao-Blackwellization allows us to integrate out the control point locations by an approximation. We apply this general methodology to multi-view reconstruction of piecewise smooth curves from multiple calibrated views in which the object has been segmented from the background. Results are shown for multiple images of two pot shards as would be encountered in archaeological applications.
{"title":"Reconstruction of objects with jagged edges through Rao-Blackwellized fitting of piecewise smooth subdivision curves","authors":"M. Kaess, F. Dellaert","doi":"10.1109/HLK.2003.1240857","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240857","url":null,"abstract":"In some applications objects are known to have non-smooth or \"jagged\" edges, which are not well approximated by smooth curves. We use subdivision curves as a simple but flexible curve representation, which allows tagging corners to model non-smooth features along otherwise smooth curves. A Markov chain Monte Carlo approach yields an approximate posterior distribution over tags, while Rao-Blackwellization allows us to integrate out the control point locations by an approximation. We apply this general methodology to multi-view reconstruction of piecewise smooth curves from multiple calibrated views in which the object has been segmented from the background. Results are shown for multiple images of two pot shards as would be encountered in archaeological applications.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125610750","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240860
G. Loy, Josephine Sullivan, S. Carlsson
A method is presented for automatically extracting key frames from an image sequence. The sequence is divided into clusters of frames with similar appearance, and the most central frame in each cluster defines a key frame. Clustering is done using an extension of the normalized cut segmentation technique based on the inter-frame similarities. The similarity between every pair of frames in the sequence is determined from the spatial image characteristics via a shape matching technique. Our algorithm is demonstrated successfully extracting 20 key frames for a tennis player in action over a 30 second (900 frame) video sequence.
{"title":"Pose-based clustering in action sequences","authors":"G. Loy, Josephine Sullivan, S. Carlsson","doi":"10.1109/HLK.2003.1240860","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240860","url":null,"abstract":"A method is presented for automatically extracting key frames from an image sequence. The sequence is divided into clusters of frames with similar appearance, and the most central frame in each cluster defines a key frame. Clustering is done using an extension of the normalized cut segmentation technique based on the inter-frame similarities. The similarity between every pair of frames in the sequence is determined from the spatial image characteristics via a shape matching technique. Our algorithm is demonstrated successfully extracting 20 key frames for a tennis player in action over a 30 second (900 frame) video sequence.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"347 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123533114","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240861
K. Schindler, Joachim Bauer
Model-based reconstruction methods are applied to the detailed reconstruction of buildings from close-range images. The 3D points obtained through image matching are segmented into a coarse polyhedral model with a robust regression algorithm, then the geometry of this model is refined with predefined shape templates in order to automatically recover a CAD-like model of the building surface. Reprojection of the 3D shape templates is used to optimally fit their parameters to the image information. Throughout the paper the investigated methods are demonstrated on real datasets.
{"title":"A model-based method for building reconstruction","authors":"K. Schindler, Joachim Bauer","doi":"10.1109/HLK.2003.1240861","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240861","url":null,"abstract":"Model-based reconstruction methods are applied to the detailed reconstruction of buildings from close-range images. The 3D points obtained through image matching are segmented into a coarse polyhedral model with a robust regression algorithm, then the geometry of this model is refined with predefined shape templates in order to automatically recover a CAD-like model of the building surface. Reprojection of the 3D shape templates is used to optimally fit their parameters to the image information. Throughout the paper the investigated methods are demonstrated on real datasets.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128217030","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240855
Kun Huang, Wei Hong, Yi Ma
Based on high-level geometric knowledge, especially symmetry, imposed upon objects in images, we demonstrate how to edit images in terms of correct 3-D shape and relationships of the objects, without explicitly performing full 3-D reconstruction. Symmetry is proposed as the central notation that unifies both conceptually and algorithmically all types of geometric regularities such as parallelism, orthogonality, and similarity. The methods are extremely simple, accurate and easy to implement, and they demonstrate the power of applying scene knowledge.
{"title":"Symmetry-based photo editing","authors":"Kun Huang, Wei Hong, Yi Ma","doi":"10.1109/HLK.2003.1240855","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240855","url":null,"abstract":"Based on high-level geometric knowledge, especially symmetry, imposed upon objects in images, we demonstrate how to edit images in terms of correct 3-D shape and relationships of the objects, without explicitly performing full 3-D reconstruction. Symmetry is proposed as the central notation that unifies both conceptually and algorithmically all types of geometric regularities such as parallelism, orthogonality, and similarity. The methods are extremely simple, accurate and easy to implement, and they demonstrate the power of applying scene knowledge.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115417971","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}
Pub Date : 2003-10-17DOI: 10.1109/HLK.2003.1240856
Slobodan Ilic, P. Fua
Deformable 3-D models can be represented either as explicit or implicit surfaces. Explicit surfaces, such as triangulations or wire-frame models, are widely accepted in the computer vision and computer graphics communities. However, for automated modeling purposes, they suffer from the fact that fitting to 2-D and 3-D image-data typically involves minimization of the Euclidean distance between observations and their closest facets, which is a non-differentiable distance function. By contrast, implicit surface representations allow fitting by minimizing an algebraic distance where one only needs to evaluate a differentiable field potential function at every data point. However, they have not gained wide acceptance because they are harder to meaningfully deform and render. To combine the strength of both approaches, we propose a method that can turn a completely arbitrary triangulated mesh, such as one taken from the Web, into an implicit surface that closely approximates its shape and can deform in tandem with it. This allows both graphics designers to deform and reshape the implicit surface by manipulating explicit surfaces using standard deformation techniques and automated fitting algorithms to take advantage of the attractive properties of implicit surfaces. We demonstrate the applicability of our technique for upper body-head, neck and shoulders-automated reconstruction.
{"title":"Generic deformable implicit mesh models for automated reconstruction","authors":"Slobodan Ilic, P. Fua","doi":"10.1109/HLK.2003.1240856","DOIUrl":"https://doi.org/10.1109/HLK.2003.1240856","url":null,"abstract":"Deformable 3-D models can be represented either as explicit or implicit surfaces. Explicit surfaces, such as triangulations or wire-frame models, are widely accepted in the computer vision and computer graphics communities. However, for automated modeling purposes, they suffer from the fact that fitting to 2-D and 3-D image-data typically involves minimization of the Euclidean distance between observations and their closest facets, which is a non-differentiable distance function. By contrast, implicit surface representations allow fitting by minimizing an algebraic distance where one only needs to evaluate a differentiable field potential function at every data point. However, they have not gained wide acceptance because they are harder to meaningfully deform and render. To combine the strength of both approaches, we propose a method that can turn a completely arbitrary triangulated mesh, such as one taken from the Web, into an implicit surface that closely approximates its shape and can deform in tandem with it. This allows both graphics designers to deform and reshape the implicit surface by manipulating explicit surfaces using standard deformation techniques and automated fitting algorithms to take advantage of the attractive properties of implicit surfaces. We demonstrate the applicability of our technique for upper body-head, neck and shoulders-automated reconstruction.","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130024437","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}
Pub Date : 1900-01-01DOI: 10.1109/hlk.2003.1240854
Feng Han, Song-Chun Zhu
{"title":"Bayesian reconstruction of 3D shapes and scenes from a single image","authors":"Feng Han, Song-Chun Zhu","doi":"10.1109/hlk.2003.1240854","DOIUrl":"https://doi.org/10.1109/hlk.2003.1240854","url":null,"abstract":"","PeriodicalId":265600,"journal":{"name":"First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114201763","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：