Pub Date : 2009-06-20DOI: 10.1109/CVPR.2009.5206683
Gutemberg Guerra-Filho
We propose novel algorithms for the detection, segmentation, recognition, and pose estimation of three-dimensional objects. Our approach initially infers geometric primitives to describe the set of 3D objects. A hierarchical structure is constructed to organize the objects in terms of shared primitives and relations between different primitives in the same object. This structure is shown to disambiguate the object models and to improve recognition rates. The primitives are obtained through our new Invariant Hough Transform. This algorithm uses geometric invariants to compute relations for subsets of points in a specific object. Each relation is stored in a hash table according to the invariant value. The hash table is used to find potential corresponding points between objects. With point matches, pose estimation is achieved by building a probability distribution of transformations. We evaluate our methods with experiments using synthetic and real 3D objects.
{"title":"Disambiguating the recognition of 3D objects","authors":"Gutemberg Guerra-Filho","doi":"10.1109/CVPR.2009.5206683","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206683","url":null,"abstract":"We propose novel algorithms for the detection, segmentation, recognition, and pose estimation of three-dimensional objects. Our approach initially infers geometric primitives to describe the set of 3D objects. A hierarchical structure is constructed to organize the objects in terms of shared primitives and relations between different primitives in the same object. This structure is shown to disambiguate the object models and to improve recognition rates. The primitives are obtained through our new Invariant Hough Transform. This algorithm uses geometric invariants to compute relations for subsets of points in a specific object. Each relation is stored in a hash table according to the invariant value. The hash table is used to find potential corresponding points between objects. With point matches, pose estimation is achieved by building a probability distribution of transformations. We evaluate our methods with experiments using synthetic and real 3D objects.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131302227","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.2009.5206617
Hoang-Hiep Vu, R. Keriven, Patrick Labatut, Jean-Philippe Pons
Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perform well on this benchmark, are still inapplicable to large-scale data sets taken under uncontrolled conditions. In this paper, we propose a multi-view stereo pipeline able to deal at the same time with very large scenes while still producing highly detailed reconstructions within very reasonable time. The keys to these benefits are twofold: (i) a minimum s-t cut based global optimization that transforms a dense point cloud into a visibility consistent mesh, followed by (ii) a mesh-based variational refinement that captures small details, smartly handling photo-consistency, regularization and adaptive resolution. Our method has been tested on numerous large-scale outdoor scenes. The accuracy of our reconstructions is also measured on the recent dense multi-view benchmark proposed by Strecha et al., showing our results to compare more than favorably with the current state-of-the-art.
{"title":"Towards high-resolution large-scale multi-view stereo","authors":"Hoang-Hiep Vu, R. Keriven, Patrick Labatut, Jean-Philippe Pons","doi":"10.1109/CVPR.2009.5206617","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206617","url":null,"abstract":"Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perform well on this benchmark, are still inapplicable to large-scale data sets taken under uncontrolled conditions. In this paper, we propose a multi-view stereo pipeline able to deal at the same time with very large scenes while still producing highly detailed reconstructions within very reasonable time. The keys to these benefits are twofold: (i) a minimum s-t cut based global optimization that transforms a dense point cloud into a visibility consistent mesh, followed by (ii) a mesh-based variational refinement that captures small details, smartly handling photo-consistency, regularization and adaptive resolution. Our method has been tested on numerous large-scale outdoor scenes. The accuracy of our reconstructions is also measured on the recent dense multi-view benchmark proposed by Strecha et al., showing our results to compare more than favorably with the current state-of-the-art.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131847950","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.2009.5206804
Sebastian Schuon, C. Theobalt, James Davis, S. Thrun
Depth maps captured with time-of-flight cameras have very low data quality: the image resolution is rather limited and the level of random noise contained in the depth maps is very high. Therefore, such flash lidars cannot be used out of the box for high-quality 3D object scanning. To solve this problem, we present LidarBoost, a 3D depth superresolution method that combines several low resolution noisy depth images of a static scene from slightly displaced viewpoints, and merges them into a high-resolution depth image. We have developed an optimization framework that uses a data fidelity term and a geometry prior term that is tailored to the specific characteristics of flash lidars. We demonstrate both visually and quantitatively that LidarBoost produces better results than previous methods from the literature.
{"title":"LidarBoost: Depth superresolution for ToF 3D shape scanning","authors":"Sebastian Schuon, C. Theobalt, James Davis, S. Thrun","doi":"10.1109/CVPR.2009.5206804","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206804","url":null,"abstract":"Depth maps captured with time-of-flight cameras have very low data quality: the image resolution is rather limited and the level of random noise contained in the depth maps is very high. Therefore, such flash lidars cannot be used out of the box for high-quality 3D object scanning. To solve this problem, we present LidarBoost, a 3D depth superresolution method that combines several low resolution noisy depth images of a static scene from slightly displaced viewpoints, and merges them into a high-resolution depth image. We have developed an optimization framework that uses a data fidelity term and a geometry prior term that is tailored to the specific characteristics of flash lidars. We demonstrate both visually and quantitatively that LidarBoost produces better results than previous methods from the literature.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115431083","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.2009.5206764
K. Hara, K. Nishino
Estimating the illumination and the reflectance properties of an object surface from a sparse set of images is an important but inherently ill-posed problem. The problem becomes even harder if we wish to account for the spatial variation of material properties on the surface. In this paper, we derive a novel method for estimating the spatially varying specular reflectance properties, of a surface of known geometry, as well as the illumination distribution from a specular-only image, for instance, captured using polarization to separate reflection components. Unlike previous work, we do not assume the illumination to be a single point light source. We model specular reflection with a spherical statistical distribution and encode the spatial variation with radial basis functions of its parameters. This allows us to formulate the simultaneous estimation of spatially varying specular reflectance and illumination as a sound probabilistic inference problem, in particular, using Csiszar's I-divergence measure. To solve it, we derive an iterative algorithm similar to expectation maximization. We demonstrate the effectiveness of the method on synthetic and real-world scenes.
{"title":"Illumination and spatially varying specular reflectance from a single view","authors":"K. Hara, K. Nishino","doi":"10.1109/CVPR.2009.5206764","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206764","url":null,"abstract":"Estimating the illumination and the reflectance properties of an object surface from a sparse set of images is an important but inherently ill-posed problem. The problem becomes even harder if we wish to account for the spatial variation of material properties on the surface. In this paper, we derive a novel method for estimating the spatially varying specular reflectance properties, of a surface of known geometry, as well as the illumination distribution from a specular-only image, for instance, captured using polarization to separate reflection components. Unlike previous work, we do not assume the illumination to be a single point light source. We model specular reflection with a spherical statistical distribution and encode the spatial variation with radial basis functions of its parameters. This allows us to formulate the simultaneous estimation of spatially varying specular reflectance and illumination as a sound probabilistic inference problem, in particular, using Csiszar's I-divergence measure. To solve it, we derive an iterative algorithm similar to expectation maximization. We demonstrate the effectiveness of the method on synthetic and real-world scenes.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115439556","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.2009.5206800
Chong Wang, D. Blei, Li Fei-Fei
Image classification and annotation are important problems in computer vision, but rarely considered together. Intuitively, annotations provide evidence for the class label, and the class label provides evidence for annotations. For example, an image of class highway is more likely annotated with words “road,” “car,” and “traffic” than words “fish,” “boat,” and “scuba.” In this paper, we develop a new probabilistic model for jointly modeling the image, its class label, and its annotations. Our model treats the class label as a global description of the image, and treats annotation terms as local descriptions of parts of the image. Its underlying probabilistic assumptions naturally integrate these two sources of information. We derive an approximate inference and estimation algorithms based on variational methods, as well as efficient approximations for classifying and annotating new images. We examine the performance of our model on two real-world image data sets, illustrating that a single model provides competitive annotation performance, and superior classification performance.
{"title":"Simultaneous image classification and annotation","authors":"Chong Wang, D. Blei, Li Fei-Fei","doi":"10.1109/CVPR.2009.5206800","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206800","url":null,"abstract":"Image classification and annotation are important problems in computer vision, but rarely considered together. Intuitively, annotations provide evidence for the class label, and the class label provides evidence for annotations. For example, an image of class highway is more likely annotated with words “road,” “car,” and “traffic” than words “fish,” “boat,” and “scuba.” In this paper, we develop a new probabilistic model for jointly modeling the image, its class label, and its annotations. Our model treats the class label as a global description of the image, and treats annotation terms as local descriptions of parts of the image. Its underlying probabilistic assumptions naturally integrate these two sources of information. We derive an approximate inference and estimation algorithms based on variational methods, as well as efficient approximations for classifying and annotating new images. We examine the performance of our model on two real-world image data sets, illustrating that a single model provides competitive annotation performance, and superior classification performance.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115540802","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.2009.5206717
Linwei Wang, Heye Zhang, Ken C. L. Wong, Huafeng Liu, P. Shi
Volumetric details of cardiac electrophysiology, such as transmembrane potential dynamics and tissue excitability of the myocardium, are of fundamental importance for understanding normal and pathological cardiac mechanisms, and for aiding the diagnosis and treatment of cardiac arrhythmia. Noninvasive observations, however, are made on body surface as an integration-projection of the volumetric phenomena inside patient's heart. We present a physiological-model-constrained statistical framework where prior knowledge of general myocardial electrical activity is used to guide the reconstruction of patient-specific volumetric cardiac electrophysiological details from body surface potential data. Sequential data assimilation with proper computational reduction is developed to estimate transmembrane potential and myocardial excitability inside the heart, which are then utilized to depict arrhythmogenic substrates. Effectiveness and validity of the framework is demonstrated through its application to evaluate the location and extent of myocardial infract using real patient data.
{"title":"Noninvasive volumetric imaging of cardiac electrophysiology","authors":"Linwei Wang, Heye Zhang, Ken C. L. Wong, Huafeng Liu, P. Shi","doi":"10.1109/CVPR.2009.5206717","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206717","url":null,"abstract":"Volumetric details of cardiac electrophysiology, such as transmembrane potential dynamics and tissue excitability of the myocardium, are of fundamental importance for understanding normal and pathological cardiac mechanisms, and for aiding the diagnosis and treatment of cardiac arrhythmia. Noninvasive observations, however, are made on body surface as an integration-projection of the volumetric phenomena inside patient's heart. We present a physiological-model-constrained statistical framework where prior knowledge of general myocardial electrical activity is used to guide the reconstruction of patient-specific volumetric cardiac electrophysiological details from body surface potential data. Sequential data assimilation with proper computational reduction is developed to estimate transmembrane potential and myocardial excitability inside the heart, which are then utilized to depict arrhythmogenic substrates. Effectiveness and validity of the framework is demonstrated through its application to evaluate the location and extent of myocardial infract using real patient data.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115772469","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.2009.5206760
Qian-Yi Zhou, U. Neumann
We present a streaming framework for seamless building reconstruction from huge aerial LiDAR point sets. By storing data as stream files on hard disk and using main memory as only a temporary storage for ongoing computation, we achieve efficient out-of-core data management. This gives us the ability to handle data sets with hundreds of millions of points in a uniform manner. By adapting a building modeling pipeline into our streaming framework, we create the whole urban model of Atlanta from 17.7 GB LiDAR data with 683 M points in under 25 hours using less than 1 GB memory. To integrate this complex modeling pipeline with our streaming framework, we develop a state propagation mechanism, and extend current reconstruction algorithms to handle the large scale of data.
{"title":"A streaming framework for seamless building reconstruction from large-scale aerial LiDAR data","authors":"Qian-Yi Zhou, U. Neumann","doi":"10.1109/CVPR.2009.5206760","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206760","url":null,"abstract":"We present a streaming framework for seamless building reconstruction from huge aerial LiDAR point sets. By storing data as stream files on hard disk and using main memory as only a temporary storage for ongoing computation, we achieve efficient out-of-core data management. This gives us the ability to handle data sets with hundreds of millions of points in a uniform manner. By adapting a building modeling pipeline into our streaming framework, we create the whole urban model of Atlanta from 17.7 GB LiDAR data with 683 M points in under 25 hours using less than 1 GB memory. To integrate this complex modeling pipeline with our streaming framework, we develop a state propagation mechanism, and extend current reconstruction algorithms to handle the large scale of data.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115881360","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.2009.5206511
Germán González, F. Fleuret, P. Fua
State-of-the-art approaches for detecting filament-like structures in noisy images rely on filters optimized for signals of a particular shape, such as an ideal edge or ridge. While these approaches are optimal when the image conforms to these ideal shapes, their performance quickly degrades on many types of real data where the image deviates from the ideal model, and when noise processes violate a Gaussian assumption. In this paper, we show that by learning rotational features, we can outperform state-of-the-art filament detection techniques on many different kinds of imagery. More specifically, we demonstrate superior performance for the detection of blood vessel in retinal scans, neurons in brightfield microscopy imagery, and streets in satellite imagery.
{"title":"Learning rotational features for filament detection","authors":"Germán González, F. Fleuret, P. Fua","doi":"10.1109/CVPR.2009.5206511","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206511","url":null,"abstract":"State-of-the-art approaches for detecting filament-like structures in noisy images rely on filters optimized for signals of a particular shape, such as an ideal edge or ridge. While these approaches are optimal when the image conforms to these ideal shapes, their performance quickly degrades on many types of real data where the image deviates from the ideal model, and when noise processes violate a Gaussian assumption. In this paper, we show that by learning rotational features, we can outperform state-of-the-art filament detection techniques on many different kinds of imagery. More specifically, we demonstrate superior performance for the detection of blood vessel in retinal scans, neurons in brightfield microscopy imagery, and streets in satellite imagery.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"36 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124383463","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.2009.5206783
José A. Rodríguez-Serrano, F. Perronnin, J. Lladós, Gemma Sánchez
This article proposes a novel similarity measure between vector sequences. Recently, a model-based approach was introduced to address this issue. It consists in modeling each sequence with a continuous Hidden Markov Model (CHMM) and computing a probabilistic measure of similarity between C-HMMs. In this paper we propose to model sequences with semi-continuous HMMs (SC-HMMs): the Gaussians of the SC-HMMs are constrained to belong to a shared pool of Gaussians. This constraint provides two major benefits. First, the a priori information contained in the common set of Gaussians leads to a more accurate estimate of the HMM parameters. Second, the computation of a probabilistic similarity between two SC-HMMs can be simplified to a Dynamic Time Warping (DTW) between their mixture weight vectors, which reduces significantly the computational cost. Experimental results on a handwritten word retrieval task show that the proposed similarity outperforms the traditional DTW between the original sequences, and the model-based approach which uses C-HMMs. We also show that this increase in accuracy can be traded against a significant reduction of the computational cost (up to 100 times).
{"title":"A similarity measure between vector sequences with application to handwritten word image retrieval","authors":"José A. Rodríguez-Serrano, F. Perronnin, J. Lladós, Gemma Sánchez","doi":"10.1109/CVPR.2009.5206783","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206783","url":null,"abstract":"This article proposes a novel similarity measure between vector sequences. Recently, a model-based approach was introduced to address this issue. It consists in modeling each sequence with a continuous Hidden Markov Model (CHMM) and computing a probabilistic measure of similarity between C-HMMs. In this paper we propose to model sequences with semi-continuous HMMs (SC-HMMs): the Gaussians of the SC-HMMs are constrained to belong to a shared pool of Gaussians. This constraint provides two major benefits. First, the a priori information contained in the common set of Gaussians leads to a more accurate estimate of the HMM parameters. Second, the computation of a probabilistic similarity between two SC-HMMs can be simplified to a Dynamic Time Warping (DTW) between their mixture weight vectors, which reduces significantly the computational cost. Experimental results on a handwritten word retrieval task show that the proposed similarity outperforms the traditional DTW between the original sequences, and the model-based approach which uses C-HMMs. We also show that this increase in accuracy can be traded against a significant reduction of the computational cost (up to 100 times).","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114413139","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.2009.5206685
Amit K. Agrawal, Yi Xu
We consider the problem of single image object motion deblurring from a static camera. It is well-known that deblurring of moving objects using a traditional camera is ill-posed, due to the loss of high spatial frequencies in the captured blurred image. A coded exposure camera modulates the integration pattern of light by opening and closing the shutter within the exposure time using a binary code. The code is chosen to make the resulting point spread function (PSF) invertible, for best deconvolution performance. However, for a successful deconvolution algorithm, PSF estimation is as important as PSF invertibility. We show that PSF estimation is easier if the resulting motion blur is smooth and the optimal code for PSF invertibility could worsen PSF estimation, since it leads to non-smooth blur. We show that both criterions of PSF invertibility and PSF estimation can be simultaneously met, albeit with a slight increase in the deconvolution noise. We propose design rules for a code to have good PSF estimation capability and outline two search criteria for finding the optimal code for a given length. We present theoretical analysis comparing the performance of the proposed code with the code optimized solely for PSF invertibility. We also show how to easily implement coded exposure on a consumer grade machine vision camera with no additional hardware. Real experimental results demonstrate the effectiveness of the proposed codes for motion deblurring.
{"title":"Coded exposure deblurring: Optimized codes for PSF estimation and invertibility","authors":"Amit K. Agrawal, Yi Xu","doi":"10.1109/CVPR.2009.5206685","DOIUrl":"https://doi.org/10.1109/CVPR.2009.5206685","url":null,"abstract":"We consider the problem of single image object motion deblurring from a static camera. It is well-known that deblurring of moving objects using a traditional camera is ill-posed, due to the loss of high spatial frequencies in the captured blurred image. A coded exposure camera modulates the integration pattern of light by opening and closing the shutter within the exposure time using a binary code. The code is chosen to make the resulting point spread function (PSF) invertible, for best deconvolution performance. However, for a successful deconvolution algorithm, PSF estimation is as important as PSF invertibility. We show that PSF estimation is easier if the resulting motion blur is smooth and the optimal code for PSF invertibility could worsen PSF estimation, since it leads to non-smooth blur. We show that both criterions of PSF invertibility and PSF estimation can be simultaneously met, albeit with a slight increase in the deconvolution noise. We propose design rules for a code to have good PSF estimation capability and outline two search criteria for finding the optimal code for a given length. We present theoretical analysis comparing the performance of the proposed code with the code optimized solely for PSF invertibility. We also show how to easily implement coded exposure on a consumer grade machine vision camera with no additional hardware. Real experimental results demonstrate the effectiveness of the proposed codes for motion deblurring.","PeriodicalId":386532,"journal":{"name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","volume":"287 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123445806","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：