Ziyang Ma, Kaiming He, Yichen Wei, Jian Sun, E. Wu
Despite the continuous advances in local stereo matching for years, most efforts are on developing robust cost computation and aggregation methods. Little attention has been seriously paid to the disparity refinement. In this work, we study weighted median filtering for disparity refinement. We discover that with this refinement, even the simple box filter aggregation achieves comparable accuracy with various sophisticated aggregation methods (with the same refinement). This is due to the nice weighted median filtering properties of removing outlier error while respecting edges/structures. This reveals that the previously overlooked refinement can be at least as crucial as aggregation. We also develop the first constant time algorithm for the previously time-consuming weighted median filter. This makes the simple combination ``box aggregation + weighted median'' an attractive solution in practice for both speed and accuracy. As a byproduct, the fast weighted median filtering unleashes its potential in other applications that were hampered by high complexities. We show its superiority in various applications such as depth up sampling, clip-art JPEG artifact removal, and image stylization.
{"title":"Constant Time Weighted Median Filtering for Stereo Matching and Beyond","authors":"Ziyang Ma, Kaiming He, Yichen Wei, Jian Sun, E. Wu","doi":"10.1109/ICCV.2013.13","DOIUrl":"https://doi.org/10.1109/ICCV.2013.13","url":null,"abstract":"Despite the continuous advances in local stereo matching for years, most efforts are on developing robust cost computation and aggregation methods. Little attention has been seriously paid to the disparity refinement. In this work, we study weighted median filtering for disparity refinement. We discover that with this refinement, even the simple box filter aggregation achieves comparable accuracy with various sophisticated aggregation methods (with the same refinement). This is due to the nice weighted median filtering properties of removing outlier error while respecting edges/structures. This reveals that the previously overlooked refinement can be at least as crucial as aggregation. We also develop the first constant time algorithm for the previously time-consuming weighted median filter. This makes the simple combination ``box aggregation + weighted median'' an attractive solution in practice for both speed and accuracy. As a byproduct, the fast weighted median filtering unleashes its potential in other applications that were hampered by high complexities. We show its superiority in various applications such as depth up sampling, clip-art JPEG artifact removal, and image stylization.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"83 1","pages":"49-56"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75015966","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}
Finding a good binary sequence is critical in determining the performance of the coded exposure imaging, but previous methods mostly rely on a random search for finding the binary codes, which could easily fail to find good long sequences due to the exponentially growing search space. In this paper, we present a new computationally efficient algorithm for generating the binary sequence, which is especially well suited for longer sequences. We show that the concept of the low autocorrelation binary sequence that has been well exploited in the information theory community can be applied for generating the fluttering patterns of the shutter, propose a new measure of a good binary sequence, and present a new algorithm by modifying the Legendre sequence for the coded exposure imaging. Experiments using both synthetic and real data show that our new algorithm consistently generates better binary sequences for the coded exposure problem, yielding better deblurring and resolution enhancement results compared to the previous methods for generating the binary codes.
{"title":"Fluttering Pattern Generation Using Modified Legendre Sequence for Coded Exposure Imaging","authors":"Hae-Gon Jeon, Joon-Young Lee, Yudeog Han, Seon Joo Kim, In-So Kweon","doi":"10.1109/ICCV.2013.128","DOIUrl":"https://doi.org/10.1109/ICCV.2013.128","url":null,"abstract":"Finding a good binary sequence is critical in determining the performance of the coded exposure imaging, but previous methods mostly rely on a random search for finding the binary codes, which could easily fail to find good long sequences due to the exponentially growing search space. In this paper, we present a new computationally efficient algorithm for generating the binary sequence, which is especially well suited for longer sequences. We show that the concept of the low autocorrelation binary sequence that has been well exploited in the information theory community can be applied for generating the fluttering patterns of the shutter, propose a new measure of a good binary sequence, and present a new algorithm by modifying the Legendre sequence for the coded exposure imaging. Experiments using both synthetic and real data show that our new algorithm consistently generates better binary sequences for the coded exposure problem, yielding better deblurring and resolution enhancement results compared to the previous methods for generating the binary codes.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"13 1","pages":"1001-1008"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75213966","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}
Optimization using the L_infty norm has been becoming an effective way to solve parameter estimation problems in multiview geometry. But the computational cost increases rapidly with the size of measurement data. Although some strategies have been presented to improve the efficiency of L_infty optimization, it is still an open issue. In the paper, we propose a novel approach under the framework of enhanced continuous tabu search (ECTS) for generic parameter estimation in multiview geometry. ECTS is an optimization method in the domain of artificial intelligence, which has an interesting ability of covering a wide solution space by promoting the search far away from current solution and consecutively decreasing the possibility of trapping in the local minima. Taking the triangulation as an example, we propose the corresponding ways in the key steps of ECTS, diversification and intensification. We also present theoretical proof to guarantee the global convergence of search with probability one. Experimental results have validated that the ECTS based approach can obtain global optimum efficiently, especially for large scale dimension of parameter. Potentially, the novel ECTS based algorithm can be applied in many applications of multiview geometry.
{"title":"Enhanced Continuous Tabu Search for Parameter Estimation in Multiview Geometry","authors":"Guoqing Zhou, Qing Wang","doi":"10.1109/ICCV.2013.402","DOIUrl":"https://doi.org/10.1109/ICCV.2013.402","url":null,"abstract":"Optimization using the L_infty norm has been becoming an effective way to solve parameter estimation problems in multiview geometry. But the computational cost increases rapidly with the size of measurement data. Although some strategies have been presented to improve the efficiency of L_infty optimization, it is still an open issue. In the paper, we propose a novel approach under the framework of enhanced continuous tabu search (ECTS) for generic parameter estimation in multiview geometry. ECTS is an optimization method in the domain of artificial intelligence, which has an interesting ability of covering a wide solution space by promoting the search far away from current solution and consecutively decreasing the possibility of trapping in the local minima. Taking the triangulation as an example, we propose the corresponding ways in the key steps of ECTS, diversification and intensification. We also present theoretical proof to guarantee the global convergence of search with probability one. Experimental results have validated that the ECTS based approach can obtain global optimum efficiently, especially for large scale dimension of parameter. Potentially, the novel ECTS based algorithm can be applied in many applications of multiview geometry.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"52 1","pages":"3240-3247"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74174954","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}
Lingxi Xie, Q. Tian, Richang Hong, Shuicheng Yan, Bo Zhang
As a special topic in computer vision, fine-grained visual categorization (FGVC) has been attracting growing attention these years. Different with traditional image classification tasks in which objects have large inter-class variation, the visual concepts in the fine-grained datasets, such as hundreds of bird species, often have very similar semantics. Due to the large inter-class similarity, it is very difficult to classify the objects without locating really discriminative features, therefore it becomes more important for the algorithm to make full use of the part information in order to train a robust model. In this paper, we propose a powerful flowchart named Hierarchical Part Matching (HPM) to cope with fine-grained classification tasks. We extend the Bag-of-Features (BoF) model by introducing several novel modules to integrate into image representation, including foreground inference and segmentation, Hierarchical Structure Learning (HSL), and Geometric Phrase Pooling (GPP). We verify in experiments that our algorithm achieves the state-of-the-art classification accuracy in the Caltech-UCSD-Birds-200-2011 dataset by making full use of the ground-truth part annotations.
{"title":"Hierarchical Part Matching for Fine-Grained Visual Categorization","authors":"Lingxi Xie, Q. Tian, Richang Hong, Shuicheng Yan, Bo Zhang","doi":"10.1109/ICCV.2013.206","DOIUrl":"https://doi.org/10.1109/ICCV.2013.206","url":null,"abstract":"As a special topic in computer vision, fine-grained visual categorization (FGVC) has been attracting growing attention these years. Different with traditional image classification tasks in which objects have large inter-class variation, the visual concepts in the fine-grained datasets, such as hundreds of bird species, often have very similar semantics. Due to the large inter-class similarity, it is very difficult to classify the objects without locating really discriminative features, therefore it becomes more important for the algorithm to make full use of the part information in order to train a robust model. In this paper, we propose a powerful flowchart named Hierarchical Part Matching (HPM) to cope with fine-grained classification tasks. We extend the Bag-of-Features (BoF) model by introducing several novel modules to integrate into image representation, including foreground inference and segmentation, Hierarchical Structure Learning (HSL), and Geometric Phrase Pooling (GPP). We verify in experiments that our algorithm achieves the state-of-the-art classification accuracy in the Caltech-UCSD-Birds-200-2011 dataset by making full use of the ground-truth part annotations.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"50 1","pages":"1641-1648"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74702930","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}
We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.
{"title":"Optimization Problems for Fast AAM Fitting in-the-Wild","authors":"Georgios Tzimiropoulos, M. Pantic","doi":"10.1109/ICCV.2013.79","DOIUrl":"https://doi.org/10.1109/ICCV.2013.79","url":null,"abstract":"We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"21 1","pages":"593-600"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75254306","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}
We present a method to identify and exploit structures that are shared across different object categories, by using sparse coding to learn a shared basis for the 'part' and 'root' templates of Deformable Part Models (DPMs).Our first contribution consists in using Shift-Invariant Sparse Coding (SISC) to learn mid-level elements that can translate during coding. This results in systematically better approximations than those attained using standard sparse coding. To emphasize that the learned mid-level structures are shiftable we call them shufflets.Our second contribution consists in using the resulting score to construct probabilistic upper bounds to the exact template scores, instead of taking them 'at face value' as is common in current works. We integrate shufflets in Dual- Tree Branch-and-Bound and cascade-DPMs and demonstrate that we can achieve a substantial acceleration, with practically no loss in performance.
{"title":"Shufflets: Shared Mid-level Parts for Fast Object Detection","authors":"Iasonas Kokkinos","doi":"10.1109/ICCV.2013.176","DOIUrl":"https://doi.org/10.1109/ICCV.2013.176","url":null,"abstract":"We present a method to identify and exploit structures that are shared across different object categories, by using sparse coding to learn a shared basis for the 'part' and 'root' templates of Deformable Part Models (DPMs).Our first contribution consists in using Shift-Invariant Sparse Coding (SISC) to learn mid-level elements that can translate during coding. This results in systematically better approximations than those attained using standard sparse coding. To emphasize that the learned mid-level structures are shiftable we call them shufflets.Our second contribution consists in using the resulting score to construct probabilistic upper bounds to the exact template scores, instead of taking them 'at face value' as is common in current works. We integrate shufflets in Dual- Tree Branch-and-Bound and cascade-DPMs and demonstrate that we can achieve a substantial acceleration, with practically no loss in performance.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"22 1","pages":"1393-1400"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72823109","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}
Dimensionality reduction for vectors in sequences is challenging since labels are attached to sequences as a whole. This paper presents a model-based dimensionality reduction method for vector sequences, namely linear sequence discriminant analysis (LSDA), which attempts to find a subspace in which sequences of the same class are projected together while those of different classes are projected as far as possible. For each sequence class, an HMM is built from states of which statistics are extracted. Means of these states are linked in order to form a mean sequence, and the variance of the sequence class is defined as the sum of all variances of component states. LSDA then learns a transformation by maximizing the separability between sequence classes and at the same time minimizing the within-sequence class scatter. DTW distance between mean sequences is used to measure the separability between sequence classes. We show that the optimization problem can be approximately transformed into an eigen decomposition problem. LDA can be seen as a special case of LSDA by considering non-sequential vectors as sequences of length one. The effectiveness of the proposed LSDA is demonstrated on two individual sequence datasets from UCI machine learning repository as well as two concatenate sequence datasets: APTI Arabic printed text database and IFN/ENIT Arabic handwriting database.
{"title":"Linear Sequence Discriminant Analysis: A Model-Based Dimensionality Reduction Method for Vector Sequences","authors":"Bing Su, Xiaoqing Ding","doi":"10.1109/ICCV.2013.115","DOIUrl":"https://doi.org/10.1109/ICCV.2013.115","url":null,"abstract":"Dimensionality reduction for vectors in sequences is challenging since labels are attached to sequences as a whole. This paper presents a model-based dimensionality reduction method for vector sequences, namely linear sequence discriminant analysis (LSDA), which attempts to find a subspace in which sequences of the same class are projected together while those of different classes are projected as far as possible. For each sequence class, an HMM is built from states of which statistics are extracted. Means of these states are linked in order to form a mean sequence, and the variance of the sequence class is defined as the sum of all variances of component states. LSDA then learns a transformation by maximizing the separability between sequence classes and at the same time minimizing the within-sequence class scatter. DTW distance between mean sequences is used to measure the separability between sequence classes. We show that the optimization problem can be approximately transformed into an eigen decomposition problem. LDA can be seen as a special case of LSDA by considering non-sequential vectors as sequences of length one. The effectiveness of the proposed LSDA is demonstrated on two individual sequence datasets from UCI machine learning repository as well as two concatenate sequence datasets: APTI Arabic printed text database and IFN/ENIT Arabic handwriting database.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"49 1","pages":"889-896"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77171732","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}
Generic object detection is the challenging task of proposing windows that localize all the objects in an image, regardless of their classes. Such detectors have recently been shown to benefit many applications such as speeding-up class-specific object detection, weakly supervised learning of object detectors and object discovery. In this paper, we introduce a novel and very efficient method for generic object detection based on a randomized version of Prim's algorithm. Using the connectivity graph of an image's super pixels, with weights modelling the probability that neighbouring super pixels belong to the same object, the algorithm generates random partial spanning trees with large expected sum of edge weights. Object localizations are proposed as bounding-boxes of those partial trees. Our method has several benefits compared to the state-of-the-art. Thanks to the efficiency of Prim's algorithm, it samples proposals very quickly: 1000 proposals are obtained in about 0.7s. With proposals bound to super pixel boundaries yet diversified by randomization, it yields very high detection rates and windows that tightly fit objects. In extensive experiments on the challenging PASCAL VOC 2007 and 2012 and SUN2012 benchmark datasets, we show that our method improves over state-of-the-art competitors for a wide range of evaluation scenarios.
{"title":"Prime Object Proposals with Randomized Prim's Algorithm","authors":"Santiago Manén, M. Guillaumin, L. Gool","doi":"10.1109/ICCV.2013.315","DOIUrl":"https://doi.org/10.1109/ICCV.2013.315","url":null,"abstract":"Generic object detection is the challenging task of proposing windows that localize all the objects in an image, regardless of their classes. Such detectors have recently been shown to benefit many applications such as speeding-up class-specific object detection, weakly supervised learning of object detectors and object discovery. In this paper, we introduce a novel and very efficient method for generic object detection based on a randomized version of Prim's algorithm. Using the connectivity graph of an image's super pixels, with weights modelling the probability that neighbouring super pixels belong to the same object, the algorithm generates random partial spanning trees with large expected sum of edge weights. Object localizations are proposed as bounding-boxes of those partial trees. Our method has several benefits compared to the state-of-the-art. Thanks to the efficiency of Prim's algorithm, it samples proposals very quickly: 1000 proposals are obtained in about 0.7s. With proposals bound to super pixel boundaries yet diversified by randomization, it yields very high detection rates and windows that tightly fit objects. In extensive experiments on the challenging PASCAL VOC 2007 and 2012 and SUN2012 benchmark datasets, we show that our method improves over state-of-the-art competitors for a wide range of evaluation scenarios.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"34 1","pages":"2536-2543"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77601515","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}
Repeated patterns (such as windows, tiles, balconies and doors) are prominent and significant features in urban scenes. Therefore, detection of these repeated patterns becomes very important for city scene analysis. This paper attacks the problem of repeated patterns detection in a precise, efficient and automatic way, by combining traditional feature extraction followed by a Kronecker product low-rank modeling approach. Our method is tailored for 2D images of building facades. We have developed algorithms for automatic selection of a representative texture within facade images using vanishing points and Harris corners. After rectifying the input images, we describe novel algorithms that extract repeated patterns by using Kronecker product based modeling that is based on a solid theoretical foundation. Our approach is unique and has not ever been used for facade analysis. We have tested our algorithms in a large set of images.
{"title":"Automatic Kronecker Product Model Based Detection of Repeated Patterns in 2D Urban Images","authors":"Juan Liu, E. Psarakis, I. Stamos","doi":"10.1109/ICCV.2013.57","DOIUrl":"https://doi.org/10.1109/ICCV.2013.57","url":null,"abstract":"Repeated patterns (such as windows, tiles, balconies and doors) are prominent and significant features in urban scenes. Therefore, detection of these repeated patterns becomes very important for city scene analysis. This paper attacks the problem of repeated patterns detection in a precise, efficient and automatic way, by combining traditional feature extraction followed by a Kronecker product low-rank modeling approach. Our method is tailored for 2D images of building facades. We have developed algorithms for automatic selection of a representative texture within facade images using vanishing points and Harris corners. After rectifying the input images, we describe novel algorithms that extract repeated patterns by using Kronecker product based modeling that is based on a solid theoretical foundation. Our approach is unique and has not ever been used for facade analysis. We have tested our algorithms in a large set of images.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"85 1","pages":"401-408"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76563391","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}
Real-world surfaces such as clothing, water and human body deform in complex ways. The image distortions observed are high-dimensional and non-linear, making it hard to estimate these deformations accurately. The recent data-driven descent approach applies Nearest Neighbor estimators iteratively on a particular distribution of training samples to obtain a globally optimal and dense deformation field between a template and a distorted image. In this work, we develop a hierarchical structure for the Nearest Neighbor estimators, each of which can have only a local image support. We demonstrate in both theory and practice that this algorithm has several advantages over the non-hierarchical version: it guarantees global optimality with significantly fewer training samples, is several orders faster, provides a metric to decide whether a given image is ``hard'' (or ``easy'') requiring more (or less) samples, and can handle more complex scenes that include both global motion and local deformation. The proposed algorithm successfully tracks a broad range of non-rigid scenes including water, clothing, and medical images, and compares favorably against several other deformation estimation and tracking approaches that do not provide optimality guarantees.
{"title":"Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation","authors":"Yuandong Tian, S. Narasimhan","doi":"10.1109/ICCV.2013.284","DOIUrl":"https://doi.org/10.1109/ICCV.2013.284","url":null,"abstract":"Real-world surfaces such as clothing, water and human body deform in complex ways. The image distortions observed are high-dimensional and non-linear, making it hard to estimate these deformations accurately. The recent data-driven descent approach applies Nearest Neighbor estimators iteratively on a particular distribution of training samples to obtain a globally optimal and dense deformation field between a template and a distorted image. In this work, we develop a hierarchical structure for the Nearest Neighbor estimators, each of which can have only a local image support. We demonstrate in both theory and practice that this algorithm has several advantages over the non-hierarchical version: it guarantees global optimality with significantly fewer training samples, is several orders faster, provides a metric to decide whether a given image is ``hard'' (or ``easy'') requiring more (or less) samples, and can handle more complex scenes that include both global motion and local deformation. The proposed algorithm successfully tracks a broad range of non-rigid scenes including water, clothing, and medical images, and compares favorably against several other deformation estimation and tracking approaches that do not provide optimality guarantees.","PeriodicalId":6351,"journal":{"name":"2013 IEEE International Conference on Computer Vision","volume":"22 1","pages":"2288-2295"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74622269","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：