Pub Date : 2008-06-04DOI: 10.1109/SMI.2008.4547985
Kunio Osada, T. Furuya, Ryutarou Ohbuchi
A local shape feature has an advantage in dealing with deformable or articulated 3D models. We evaluate the performance of our local, 2D visual features and their integration method based on the bag-of-features approach using the SHREC'08 CAD model track. The evaluation showed that, it performed very well, winning the 2nd place in the contest, although it lost to a method that employs supervised learning of classes in the benchmark dataset.
{"title":"SHREC—08 entry: Local 2D visual features for CAD Model retrieval","authors":"Kunio Osada, T. Furuya, Ryutarou Ohbuchi","doi":"10.1109/SMI.2008.4547985","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547985","url":null,"abstract":"A local shape feature has an advantage in dealing with deformable or articulated 3D models. We evaluate the performance of our local, 2D visual features and their integration method based on the bag-of-features approach using the SHREC'08 CAD model track. The evaluation showed that, it performed very well, winning the 2nd place in the contest, although it lost to a method that employs supervised learning of classes in the benchmark dataset.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128568575","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547959
Charlie C. L. Wang
Following the definition of developable surface in differential geometry, the flattenable mesh surface, a special type of piecewise- linear surface, inherits the good property of developable surface about having an isometric map from its 3D shape to a corresponding planar region. Different from the developable surfaces, a flattenable mesh surface is more flexible to model objects with complex shapes (e.g., cramped paper or warped leather with wrinkles). Modelling a flattenable mesh from a given input mesh surface can be completed under a constrained nonlinear optimization framework. In this paper, we reformulate the problem in terms of estimation error. Therefore, the shape of a flattenable mesh can be computed by the least-norm solutions faster. Moreover, the method for adding shape constraints to the modelling of flattenable mesh surfaces has been exploited. We show that the proposed method can compute flattenable mesh surfaces from input piecewise linear surfaces successfully and efficiently.
{"title":"A least-norm approach to flattenable mesh surface processing","authors":"Charlie C. L. Wang","doi":"10.1109/SMI.2008.4547959","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547959","url":null,"abstract":"Following the definition of developable surface in differential geometry, the flattenable mesh surface, a special type of piecewise- linear surface, inherits the good property of developable surface about having an isometric map from its 3D shape to a corresponding planar region. Different from the developable surfaces, a flattenable mesh surface is more flexible to model objects with complex shapes (e.g., cramped paper or warped leather with wrinkles). Modelling a flattenable mesh from a given input mesh surface can be completed under a constrained nonlinear optimization framework. In this paper, we reformulate the problem in terms of estimation error. Therefore, the shape of a flattenable mesh can be computed by the least-norm solutions faster. Moreover, the method for adding shape constraints to the modelling of flattenable mesh surfaces has been exploited. We show that the proposed method can compute flattenable mesh surfaces from input piecewise linear surfaces successfully and efficiently.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125941322","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547986
A. I. Wagan, A. Godil, Xiaolan Li
In this paper we propose a novel algorithm for 3D shape searching based on the visual similarity by cutting the object into sections. This method rectifies some of the shortcomings of the visual similarity based methods, so that it can better account for concave areas of an object and parts of the object not visible because of occlusion. As the first step, silhouettes of the 3D object are generated by partitioning the object into number of parts with cutting planes perpendicular to the view direction. Then Zernike moments are applied on the silhouettes to generate shape descriptors. The distance measure is based on minimizing the distance among all the combinations of shape descriptors and then these distances are used for similarity based searching. We have performed experiments on the Princeton shape benchmark and the Purdue CAD/CAM database, and have achieved results comparable to some of the best algorithms in the 3D shape searching literature.
{"title":"SHREC’08 entry: 3D shape searching using object partitioning","authors":"A. I. Wagan, A. Godil, Xiaolan Li","doi":"10.1109/SMI.2008.4547986","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547986","url":null,"abstract":"In this paper we propose a novel algorithm for 3D shape searching based on the visual similarity by cutting the object into sections. This method rectifies some of the shortcomings of the visual similarity based methods, so that it can better account for concave areas of an object and parts of the object not visible because of occlusion. As the first step, silhouettes of the 3D object are generated by partitioning the object into number of parts with cutting planes perpendicular to the view direction. Then Zernike moments are applied on the silhouettes to generate shape descriptors. The distance measure is based on minimizing the distance among all the combinations of shape descriptors and then these distances are used for similarity based searching. We have performed experiments on the Princeton shape benchmark and the Purdue CAD/CAM database, and have achieved results comparable to some of the best algorithms in the 3D shape searching literature.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"275 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123305804","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547938
Tianyun Ni, Young In Yeo, A. Myles, V. Goel, J. Peters
We present a fast algorithm for converting quad meshes on the GPU to smooth surfaces. Meshes with 12,000 input quads, of which 60% have one or more non-4-valent vertices, are converted, evaluated and rendered with 9times9 resolution per quad at 50 frames per second. The conversion reproduces bi-cubic splines wherever possible and closely mimics the shape of the Catmull-Clark subdivision surface by c-patches where a vertex has a valence different from 4. The smooth surface is piecewise polynomial and has well-defined normals everywhere. The evaluation avoids pixel dropout.
{"title":"GPU smoothing of quad meshes","authors":"Tianyun Ni, Young In Yeo, A. Myles, V. Goel, J. Peters","doi":"10.1109/SMI.2008.4547938","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547938","url":null,"abstract":"We present a fast algorithm for converting quad meshes on the GPU to smooth surfaces. Meshes with 12,000 input quads, of which 60% have one or more non-4-valent vertices, are converted, evaluated and rendered with 9times9 resolution per quad at 50 frames per second. The conversion reproduces bi-cubic splines wherever possible and closely mimics the shape of the Catmull-Clark subdivision surface by c-patches where a vertex has a valence different from 4. The smooth surface is piecewise polynomial and has well-defined normals everywhere. The evaluation avoids pixel dropout.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121095131","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547983
Corey Goldfeder, Haoyun Feng, P. Allen
Training a 3D model classifier on a small dataset is very challenging. However, large datasets of partially classified models are now commonly available online. We use an external training set of models with associated text tags to automatically assign tags to both training and query models. The similarity between these tags, used in conjunction with a standard shape descriptor, yields a multiclassifier that outperforms the standalone shape descriptor.
{"title":"SHREC’08 entry: Training set expansion via autotags","authors":"Corey Goldfeder, Haoyun Feng, P. Allen","doi":"10.1109/SMI.2008.4547983","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547983","url":null,"abstract":"Training a 3D model classifier on a small dataset is very challenging. However, large datasets of partially classified models are now commonly available online. We use an external training set of models with associated text tags to automatically assign tags to both training and query models. The similarity between these tags, used in conjunction with a standard shape descriptor, yields a multiclassifier that outperforms the standalone shape descriptor.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"268 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121982955","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547958
M. Aigner, B. Jüttler
We describe Gauss-Newton type methods for fitting implicitly defined curves and surfaces to given unorganized data points. The methods can deal with general error functions, such as approximations to the l1 or linfin norm of the vector of residuals. Depending on the definition of the residuals, we distinguish between direct and data-based methods. In addition, we show that these methods can either be seen as (discrete) iterative methods, where an update of the unknown shape parameters is computed in each step, or as continuous evolution processes, that generate a time-dependent family of curves or surfaces, which converges towards the final result. It is shown that the data-based methods - which are less costly, as they work without the need of computing the closest points - can efficiently deal with error functions that are adapted to noisy and uncertain data. In addition, we observe that the interpretation as evolution process allows to deal with the issues of regularization and with additional constraints.
{"title":"Gauss-Newton-type techniques for robustly fitting implicitly defined curves and surfaces to unorganized data points","authors":"M. Aigner, B. Jüttler","doi":"10.1109/SMI.2008.4547958","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547958","url":null,"abstract":"We describe Gauss-Newton type methods for fitting implicitly defined curves and surfaces to given unorganized data points. The methods can deal with general error functions, such as approximations to the l1 or linfin norm of the vector of residuals. Depending on the definition of the residuals, we distinguish between direct and data-based methods. In addition, we show that these methods can either be seen as (discrete) iterative methods, where an update of the unknown shape parameters is computed in each step, or as continuous evolution processes, that generate a time-dependent family of curves or surfaces, which converges towards the final result. It is shown that the data-based methods - which are less costly, as they work without the need of computing the closest points - can efficiently deal with error functions that are adapted to noisy and uncertain data. In addition, we observe that the interpretation as evolution process allows to deal with the issues of regularization and with additional constraints.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133515814","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 : 2008-06-04DOI: 10.1109/SMI.2008.4547945
Xianfang Sun, Paul L. Rosin, Ralph Robert Martin, F. Langbein
This paper discusses noise in range data measured by a Konica Minolta Vivid 910 scanner. Previous papers considering denoising 3D mesh data have often used artificial data comprising Gaussian noise, which is independently distributed at each mesh point. Measurements of an accurately machined, almost planar test surface indicate that real scanner data does not have such properties. An initial characterisation of real scanner noise for this test surface shows that the errors are not quite Gaussian, and more importantly, exhibit significant short range correlation. This analysis yields a simple model for generating noise with similar characteristics. We also examine the effect of two typical mesh denoising algorithms on the real noise present in the test data. The results show that new denoising algorithms are required to effectively remove real scanner noise.
{"title":"Noise in 3D laser range scanner data","authors":"Xianfang Sun, Paul L. Rosin, Ralph Robert Martin, F. Langbein","doi":"10.1109/SMI.2008.4547945","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547945","url":null,"abstract":"This paper discusses noise in range data measured by a Konica Minolta Vivid 910 scanner. Previous papers considering denoising 3D mesh data have often used artificial data comprising Gaussian noise, which is independently distributed at each mesh point. Measurements of an accurately machined, almost planar test surface indicate that real scanner data does not have such properties. An initial characterisation of real scanner noise for this test surface shows that the errors are not quite Gaussian, and more importantly, exhibit significant short range correlation. This analysis yields a simple model for generating noise with similar characteristics. We also examine the effect of two typical mesh denoising algorithms on the real noise present in the test data. The results show that new denoising algorithms are required to effectively remove real scanner noise.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128624479","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 : 2008-06-01DOI: 10.1109/SMI.2008.4547994
S. Berretti, A. Bimbo, P. Pala
In this work, we shortly describe an original 3D face recognition approach and its performance as resulted from the 3D Shape Retrieval Contest of 3D Face Scans organized by SHREC 2008 with the support of the Network of Excellence AIM copySHAPE. In particular, the evaluation shows that the proposed approach attains the highest performance on the SHREC 2008 data set.
{"title":"SHREC’08 entry: 3D face recognition using integral shape information","authors":"S. Berretti, A. Bimbo, P. Pala","doi":"10.1109/SMI.2008.4547994","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547994","url":null,"abstract":"In this work, we shortly describe an original 3D face recognition approach and its performance as resulted from the 3D Shape Retrieval Contest of 3D Face Scans organized by SHREC 2008 with the support of the Network of Excellence AIM copySHAPE. In particular, the evaluation shows that the proposed approach attains the highest performance on the SHREC 2008 data set.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132601721","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 : 2008-04-20DOI: 10.1109/SMI.2008.4547947
S. Bilir, Y. Yemez, C. Okluortam, Görü Ve, Grafik Laboratuvarı, Koç¨universitesi, Istanbul, Giris¸dinamik
We present a fast deformation-based method for building time-varying surface models of dynamic objects from multiview video streams. Starting from an initial mesh representation, the surface of a dynamic object is tracked over time, both in geometry and connectivity, based on multiview silhouette information via a mesh-based deformation technique. The resulting smooth time-varying surface is then represented as a mesh sequence that can efficiently be encoded in terms of mesh restructuring operations and small-scale vertex displacements along with the initial model. Another advantage of the proposed method is the ability to deal with dynamic objects that may undergo a nonrigid transformation. We demonstrate the performance of the presented method on a synthetic human body model sequence.
{"title":"Time varying surface reconstruction from multiview video","authors":"S. Bilir, Y. Yemez, C. Okluortam, Görü Ve, Grafik Laboratuvarı, Koç¨universitesi, Istanbul, Giris¸dinamik","doi":"10.1109/SMI.2008.4547947","DOIUrl":"https://doi.org/10.1109/SMI.2008.4547947","url":null,"abstract":"We present a fast deformation-based method for building time-varying surface models of dynamic objects from multiview video streams. Starting from an initial mesh representation, the surface of a dynamic object is tracked over time, both in geometry and connectivity, based on multiview silhouette information via a mesh-based deformation technique. The resulting smooth time-varying surface is then represented as a mesh sequence that can efficiently be encoded in terms of mesh restructuring operations and small-scale vertex displacements along with the initial model. Another advantage of the proposed method is the ability to deal with dynamic objects that may undergo a nonrigid transformation. We demonstrate the performance of the presented method on a synthetic human body model sequence.","PeriodicalId":118774,"journal":{"name":"2008 IEEE International Conference on Shape Modeling and Applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128262011","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：