Pub Date : 2009-06-20DOI: 10.1109/CVPR.2009.5206849
M. Toews, W. Wells
This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-rank) descriptors outperform other state-of-the-art descriptors in terms of precision-recall, including standard SIFT and GLOH.
{"title":"SIFT-Rank: Ordinal description for invariant feature correspondence","authors":"M. Toews, W. Wells","doi":"10.1109/CVPR.2009.5206849","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206849","url":null,"abstract":"This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves as a simple, non-parametric substitute for ad hoc scaling and thresholding techniques currently used. Ordinal description is particularly well-suited for invariant features, as the high dimensionality of state-of-the-art descriptors permits a large number of unique rank-orderings, and the computationally complex step of sorting is only required once after geometrical normalization. Correspondence trials based on a benchmark data set show that in general, rank-ordered SIFT (SIFT-rank) descriptors outperform other state-of-the-art descriptors in terms of precision-recall, including standard SIFT and GLOH.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130719068","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206509
Lifeng Shang, Kwok-Ping Chan
This paper presents a nonparametric discriminant HMM and applies it to facial expression recognition. In the proposed HMM, we introduce an effective nonparametric output probability estimation method to increase the discrimination ability at both hidden state level and class level. The proposed method uses a nonparametric adaptive kernel to utilize information from all classes and improve the discrimination at class level. The discrimination between hidden states is increased by defining membership coefficients which associate each reference vector with hidden states. The adaption of such coefficients is obtained by the expectation maximization (EM) method. Furthermore, we present a general formula for the estimation of output probability, which provides a way to develop new HMMs. Finally, we evaluate the performance of the proposed method on the CMU expression database and compare it with other nonparametric HMMs.
{"title":"Nonparametric discriminant HMM and application to facial expression recognition","authors":"Lifeng Shang, Kwok-Ping Chan","doi":"10.1109/CVPR.2009.5206509","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206509","url":null,"abstract":"This paper presents a nonparametric discriminant HMM and applies it to facial expression recognition. In the proposed HMM, we introduce an effective nonparametric output probability estimation method to increase the discrimination ability at both hidden state level and class level. The proposed method uses a nonparametric adaptive kernel to utilize information from all classes and improve the discrimination at class level. The discrimination between hidden states is increased by defining membership coefficients which associate each reference vector with hidden states. The adaption of such coefficients is obtained by the expectation maximization (EM) method. Furthermore, we present a general formula for the estimation of output probability, which provides a way to develop new HMMs. Finally, we evaluate the performance of the proposed method on the CMU expression database and compare it with other nonparametric HMMs.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130968026","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206810
Marcel Brückner, Ferid Bajramovic, Joachim Denzler
Detecting image pairs with a common field of view is an important prerequisite for many computer vision tasks. Typically, common local features are used as a criterion for identifying such image pairs. This approach, however, requires a reliable method for matching features, which is generally a very difficult problem, especially in situations with a wide baseline or ambiguities in the scene. We propose two new approaches for the common field of view problem. The first one is still based on feature matching. Instead of requiring a very low false positive rate for the feature matching, however, geometric constraints are used to assess matches which may contain many false positives. The second approach completely avoids hard matching of features by evaluating the entropy of correspondence probabilities. We perform quantitative experiments on three different hand labeled scenes with varying difficulty. In moderately difficult situations with a medium baseline and few ambiguities in the scene, our proposed methods give similarly good results to the classical matching based method. On the most challenging scene having a wide baseline and many ambiguities, the performance of the classical method deteriorates, while ours are much less affected and still produce good results. Hence, our methods show the best overall performance in a combined evaluation.
{"title":"Geometric and probabilistic image dissimilarity measures for common field of view detection","authors":"Marcel Brückner, Ferid Bajramovic, Joachim Denzler","doi":"10.1109/CVPR.2009.5206810","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206810","url":null,"abstract":"Detecting image pairs with a common field of view is an important prerequisite for many computer vision tasks. Typically, common local features are used as a criterion for identifying such image pairs. This approach, however, requires a reliable method for matching features, which is generally a very difficult problem, especially in situations with a wide baseline or ambiguities in the scene. We propose two new approaches for the common field of view problem. The first one is still based on feature matching. Instead of requiring a very low false positive rate for the feature matching, however, geometric constraints are used to assess matches which may contain many false positives. The second approach completely avoids hard matching of features by evaluating the entropy of correspondence probabilities. We perform quantitative experiments on three different hand labeled scenes with varying difficulty. In moderately difficult situations with a medium baseline and few ambiguities in the scene, our proposed methods give similarly good results to the classical matching based method. On the most challenging scene having a wide baseline and many ambiguities, the performance of the classical method deteriorates, while ours are much less affected and still produce good results. Hence, our methods show the best overall performance in a combined evaluation.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133324071","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206647
H. Cooper, R. Bowden
This paper introduces a fully automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Based on head and hand tracking, a novel temporally constrained adaptation of a priori mining is used to extract similar regions of video, with the aid of a proposed contextual negative selection method. These regions are refined in the temporal domain to isolate the occurrences of similar signs in each example. The system is shown to automatically identify and segment signs from standard news broadcasts containing a variety of topics.
{"title":"Learning signs from subtitles: A weakly supervised approach to sign language recognition","authors":"H. Cooper, R. Bowden","doi":"10.1109/CVPR.2009.5206647","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206647","url":null,"abstract":"This paper introduces a fully automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Based on head and hand tracking, a novel temporally constrained adaptation of a priori mining is used to extract similar regions of video, with the aid of a proposed contextual negative selection method. These regions are refined in the temporal domain to isolate the occurrences of similar signs in each example. The system is shown to automatically identify and segment signs from standard news broadcasts containing a variety of topics.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132144116","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206753
Tom Haber, Christian Fuchs, P. Bekaert, H. Seidel, M. Goesele, H. Lensch
We present an approach for recovering the reflectance of a static scene with known geometry from a collection of images taken under distant, unknown illumination. In contrast to previous work, we allow the illumination to vary between the images, which greatly increases the applicability of the approach. Using an all-frequency relighting framework based on wavelets, we are able to simultaneously estimate the per-image incident illumination and the per-surface point reflectance. The wavelet framework allows for incorporating various reflection models. We demonstrate the quality of our results for synthetic test cases as well as for several datasets captured under laboratory conditions. Combined with multi-view stereo reconstruction, we are even able to recover the geometry and reflectance of a scene solely using images collected from the Internet.
{"title":"Relighting objects from image collections","authors":"Tom Haber, Christian Fuchs, P. Bekaert, H. Seidel, M. Goesele, H. Lensch","doi":"10.1109/CVPR.2009.5206753","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206753","url":null,"abstract":"We present an approach for recovering the reflectance of a static scene with known geometry from a collection of images taken under distant, unknown illumination. In contrast to previous work, we allow the illumination to vary between the images, which greatly increases the applicability of the approach. Using an all-frequency relighting framework based on wavelets, we are able to simultaneously estimate the per-image incident illumination and the per-surface point reflectance. The wavelet framework allows for incorporating various reflection models. We demonstrate the quality of our results for synthetic test cases as well as for several datasets captured under laboratory conditions. Combined with multi-view stereo reconstruction, we are even able to recover the geometry and reflectance of a scene solely using images collected from the Internet.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132450800","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206871
W. Liu, Shih-Fu Chang
Graph-based methods form a main category of semi-supervised learning, offering flexibility and easy implementation in many applications. However, the performance of these methods is often sensitive to the construction of a neighborhood graph, which is non-trivial for many real-world problems. In this paper, we propose a novel framework that builds on learning the graph given labeled and unlabeled data. The paper has two major contributions. Firstly, we use a nonparametric algorithm to learn the entire adjacency matrix of a symmetry-favored k-NN graph, assuming that the matrix is doubly stochastic. The nonparametric algorithm makes the constructed graph highly robust to noisy samples and capable of approximating underlying submanifolds or clusters. Secondly, to address multi-class semi-supervised classification, we formulate a constrained label propagation problem on the learned graph by incorporating class priors, leading to a simple closed-form solution. Experimental results on both synthetic and real-world datasets show that our approach is significantly better than the state-of-the-art graph-based semi-supervised learning algorithms in terms of accuracy and robustness.
{"title":"Robust multi-class transductive learning with graphs","authors":"W. Liu, Shih-Fu Chang","doi":"10.1109/CVPR.2009.5206871","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206871","url":null,"abstract":"Graph-based methods form a main category of semi-supervised learning, offering flexibility and easy implementation in many applications. However, the performance of these methods is often sensitive to the construction of a neighborhood graph, which is non-trivial for many real-world problems. In this paper, we propose a novel framework that builds on learning the graph given labeled and unlabeled data. The paper has two major contributions. Firstly, we use a nonparametric algorithm to learn the entire adjacency matrix of a symmetry-favored k-NN graph, assuming that the matrix is doubly stochastic. The nonparametric algorithm makes the constructed graph highly robust to noisy samples and capable of approximating underlying submanifolds or clusters. Secondly, to address multi-class semi-supervised classification, we formulate a constrained label propagation problem on the learned graph by incorporating class priors, leading to a simple closed-form solution. Experimental results on both synthetic and real-world datasets show that our approach is significantly better than the state-of-the-art graph-based semi-supervised learning algorithms in terms of accuracy and robustness.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132751541","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206754
Mykhaylo Andriluka, S. Roth, B. Schiele
Non-rigid object detection and articulated pose estimation are two related and challenging problems in computer vision. Numerous models have been proposed over the years and often address different special cases, such as pedestrian detection or upper body pose estimation in TV footage. This paper shows that such specialization may not be necessary, and proposes a generic approach based on the pictorial structures framework. We show that the right selection of components for both appearance and spatial modeling is crucial for general applicability and overall performance of the model. The appearance of body parts is modeled using densely sampled shape context descriptors and discriminatively trained AdaBoost classifiers. Furthermore, we interpret the normalized margin of each classifier as likelihood in a generative model. Non-Gaussian relationships between parts are represented as Gaussians in the coordinate system of the joint between parts. The marginal posterior of each part is inferred using belief propagation. We demonstrate that such a model is equally suitable for both detection and pose estimation tasks, outperforming the state of the art on three recently proposed datasets.
{"title":"Pictorial structures revisited: People detection and articulated pose estimation","authors":"Mykhaylo Andriluka, S. Roth, B. Schiele","doi":"10.1109/CVPR.2009.5206754","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206754","url":null,"abstract":"Non-rigid object detection and articulated pose estimation are two related and challenging problems in computer vision. Numerous models have been proposed over the years and often address different special cases, such as pedestrian detection or upper body pose estimation in TV footage. This paper shows that such specialization may not be necessary, and proposes a generic approach based on the pictorial structures framework. We show that the right selection of components for both appearance and spatial modeling is crucial for general applicability and overall performance of the model. The appearance of body parts is modeled using densely sampled shape context descriptors and discriminatively trained AdaBoost classifiers. Furthermore, we interpret the normalized margin of each classifier as likelihood in a generative model. Non-Gaussian relationships between parts are represented as Gaussians in the coordinate system of the joint between parts. The marginal posterior of each part is inferred using belief propagation. We demonstrate that such a model is equally suitable for both detection and pose estimation tasks, outperforming the state of the art on three recently proposed datasets.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131462900","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206554
John C. Femiani, A. Razdan
The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB coordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.
{"title":"Interval HSV: Extracting ink annotations","authors":"John C. Femiani, A. Razdan","doi":"10.1109/CVPR.2009.5206554","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206554","url":null,"abstract":"The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB coordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128813840","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206675
Fei Wang, Xin Wang, Ta-Hsin Li
Linear discriminant analysis (LDA) is a popular feature extraction method that has aroused considerable interests in computer vision and pattern recognition fields. The projection vectors of LDA is usually achieved by maximizing the between-class scatter and simultaneously minimizing the within-class scatter of the data set. However, in practice, there is usually a lack of sufficient labeled data, which makes the estimated projection direction inaccurate. To address the above limitations, in this paper, we propose a novel semi-supervised discriminant analysis approach. Unlike traditional graph based methods, our algorithm incorporates the geometric information revealed by both labeled and unlabeled data points in a semi-parametric way. Specifically, the final projections of the data points will contain two parts: a discriminant part learned by traditional LDA (or KDA) on the labeled points and a geometrical part learned by kernel PCA on the whole data set. Therefore we call our algorithm semi-parametric semi-supervised discriminant analysis (SSDA). Experimental results on face recognition and image retrieval tasks are presented to show the effectiveness of our method.
{"title":"Beyond the graphs: Semi-parametric semi-supervised discriminant analysis","authors":"Fei Wang, Xin Wang, Ta-Hsin Li","doi":"10.1109/CVPR.2009.5206675","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206675","url":null,"abstract":"Linear discriminant analysis (LDA) is a popular feature extraction method that has aroused considerable interests in computer vision and pattern recognition fields. The projection vectors of LDA is usually achieved by maximizing the between-class scatter and simultaneously minimizing the within-class scatter of the data set. However, in practice, there is usually a lack of sufficient labeled data, which makes the estimated projection direction inaccurate. To address the above limitations, in this paper, we propose a novel semi-supervised discriminant analysis approach. Unlike traditional graph based methods, our algorithm incorporates the geometric information revealed by both labeled and unlabeled data points in a semi-parametric way. Specifically, the final projections of the data points will contain two parts: a discriminant part learned by traditional LDA (or KDA) on the labeled points and a geometrical part learned by kernel PCA on the whole data set. Therefore we call our algorithm semi-parametric semi-supervised discriminant analysis (SSDA). Experimental results on face recognition and image retrieval tasks are presented to show the effectiveness of our method.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127650339","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 : 2009-06-20DOI: 10.1109/CVPR.2009.5206591
Fabio Galasso, Joan Lasenby
Since the pioneering work of Gibson in 1950, Shape-From-Texture has been considered by researchers as a hard problem, mainly due to restrictive assumptions which often limit its applicability. We assume a very general stochastic homogeneity and perspective camera model, for both deterministic and stochastic textures. A multi-scale distortion is efficiently estimated with a previously presented method based on Fourier analysis and Gabor filters. The novel 3D reconstruction method that we propose applies to general shapes, and includes non-developable and extensive surfaces. Our algorithm is accurate, robust and compares favorably to the present state of the art of Shape-From-Texture. Results show its application to non-invasively study shape changes with laid-on textures, while rendering and re-texturing of cloth is suggested for future work.
{"title":"Fourier analysis and Gabor filtering for texture analysis and local reconstruction of general shapes","authors":"Fabio Galasso, Joan Lasenby","doi":"10.1109/CVPR.2009.5206591","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206591","url":null,"abstract":"Since the pioneering work of Gibson in 1950, Shape-From-Texture has been considered by researchers as a hard problem, mainly due to restrictive assumptions which often limit its applicability. We assume a very general stochastic homogeneity and perspective camera model, for both deterministic and stochastic textures. A multi-scale distortion is efficiently estimated with a previously presented method based on Fourier analysis and Gabor filters. The novel 3D reconstruction method that we propose applies to general shapes, and includes non-developable and extensive surfaces. Our algorithm is accurate, robust and compares favorably to the present state of the art of Shape-From-Texture. Results show its application to non-invasively study shape changes with laid-on textures, while rendering and re-texturing of cloth is suggested for future work.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127816939","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：