We present a practical approach to address the problem of unconstrained face alignment for a single image. In our unconstrained problem, we need to deal with large shape and appearance variations under extreme head poses and rich shape deformation. To equip cascaded regressors with the capability to handle global shape variation and irregular appearance-shape relation in the unconstrained scenario, we partition the optimisation space into multiple domains of homogeneous descent, and predict a shape as a composition of estimations from multiple domain-specific regressors. With a specially formulated learning objective and a novel tree splitting function, our approach is capable of estimating a robust and meaningful composition. In addition to achieving state-of-the-art accuracy over existing approaches, our framework is also an efficient solution (350 FPS), thanks to the on-the-fly domain exclusion mechanism and the capability of leveraging the fast pixel feature.
{"title":"Unconstrained Face Alignment via Cascaded Compositional Learning","authors":"Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang","doi":"10.1109/CVPR.2016.371","DOIUrl":"https://doi.org/10.1109/CVPR.2016.371","url":null,"abstract":"We present a practical approach to address the problem of unconstrained face alignment for a single image. In our unconstrained problem, we need to deal with large shape and appearance variations under extreme head poses and rich shape deformation. To equip cascaded regressors with the capability to handle global shape variation and irregular appearance-shape relation in the unconstrained scenario, we partition the optimisation space into multiple domains of homogeneous descent, and predict a shape as a composition of estimations from multiple domain-specific regressors. With a specially formulated learning objective and a novel tree splitting function, our approach is capable of estimating a robust and meaningful composition. In addition to achieving state-of-the-art accuracy over existing approaches, our framework is also an efficient solution (350 FPS), thanks to the on-the-fly domain exclusion mechanism and the capability of leveraging the fast pixel feature.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"C-31 1","pages":"3409-3417"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84443379","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}
Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.
{"title":"Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence","authors":"J. Xie, M. Wang, Yi Fang","doi":"10.1109/CVPR.2016.360","DOIUrl":"https://doi.org/10.1109/CVPR.2016.360","url":null,"abstract":"Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"148 Pt 7 1","pages":"3309-3317"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84084001","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}
In this paper we consider the problem of visual saliency modeling, including both human gaze prediction and salient object segmentation. The overarching goal of the paper is to identify high level considerations relevant to deriving more sophisticated visual saliency models. A deep learning model based on fully convolutional networks (FCNs) is presented, which shows very favorable performance across a wide variety of benchmarks relative to existing proposals. We also demonstrate that the manner in which training data is selected, and ground truth treated is critical to resulting model behaviour. Recent efforts have explored the relationship between human gaze and salient objects, and we also examine this point further in the context of FCNs. Close examination of the proposed and alternative models serves as a vehicle for identifying problems important to developing more comprehensive models going forward.
{"title":"A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond","authors":"Neil D. B. Bruce, Christopher Catton, Sasa Janjic","doi":"10.1109/CVPR.2016.62","DOIUrl":"https://doi.org/10.1109/CVPR.2016.62","url":null,"abstract":"In this paper we consider the problem of visual saliency modeling, including both human gaze prediction and salient object segmentation. The overarching goal of the paper is to identify high level considerations relevant to deriving more sophisticated visual saliency models. A deep learning model based on fully convolutional networks (FCNs) is presented, which shows very favorable performance across a wide variety of benchmarks relative to existing proposals. We also demonstrate that the manner in which training data is selected, and ground truth treated is critical to resulting model behaviour. Recent efforts have explored the relationship between human gaze and salient objects, and we also examine this point further in the context of FCNs. Close examination of the proposed and alternative models serves as a vehicle for identifying problems important to developing more comprehensive models going forward.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"516-524"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80997842","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}
Video object segmentation is challenging due to fast moving objects, deforming shapes, and cluttered backgrounds. Optical flow can be used to propagate an object segmentation over time but, unfortunately, flow is often inaccurate, particularly around object boundaries. Such boundaries are precisely where we want our segmentation to be accurate. To obtain accurate segmentation across time, we propose an efficient algorithm that considers video segmentation and optical flow estimation simultaneously. For video segmentation, we formulate a principled, multiscale, spatio-temporal objective function that uses optical flow to propagate information between frames. For optical flow estimation, particularly at object boundaries, we compute the flow independently in the segmented regions and recompose the results. We call the process object flow and demonstrate the effectiveness of jointly optimizing optical flow and video segmentation using an iterative scheme. Experiments on the SegTrack v2 and Youtube-Objects datasets show that the proposed algorithm performs favorably against the other state-of-the-art methods.
{"title":"Video Segmentation via Object Flow","authors":"Yi-Hsuan Tsai, Ming-Hsuan Yang, Michael J. Black","doi":"10.1109/CVPR.2016.423","DOIUrl":"https://doi.org/10.1109/CVPR.2016.423","url":null,"abstract":"Video object segmentation is challenging due to fast moving objects, deforming shapes, and cluttered backgrounds. Optical flow can be used to propagate an object segmentation over time but, unfortunately, flow is often inaccurate, particularly around object boundaries. Such boundaries are precisely where we want our segmentation to be accurate. To obtain accurate segmentation across time, we propose an efficient algorithm that considers video segmentation and optical flow estimation simultaneously. For video segmentation, we formulate a principled, multiscale, spatio-temporal objective function that uses optical flow to propagate information between frames. For optical flow estimation, particularly at object boundaries, we compute the flow independently in the segmented regions and recompose the results. We call the process object flow and demonstrate the effectiveness of jointly optimizing optical flow and video segmentation using an iterative scheme. Experiments on the SegTrack v2 and Youtube-Objects datasets show that the proposed algorithm performs favorably against the other state-of-the-art methods.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"51 1","pages":"3899-3908"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82998354","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}
The appearance of (outdoor) scenes changes considerably with the strength of certain transient attributes, such as "rainy", "dark" or "sunny". Obviously, this also affects the representation of an image in feature space, e.g., as activations at a certain CNN layer, and consequently impacts scene recognition performance. In this work, we investigate the variability in these transient attributes as a rich source of information for studying how image representations change as a function of attribute strength. In particular, we leverage a recently introduced dataset with fine-grain annotations to estimate feature trajectories for a collection of transient attributes and then show how these trajectories can be transferred to new image representations. This enables us to synthesize new data along the transferred trajectories with respect to the dimensions of the space spanned by the transient attributes. Applicability of this concept is demonstrated on the problem of oneshot recognition of scene locations. We show that data synthesized via feature trajectory transfer considerably boosts recognition performance, (1) with respect to baselines and (2) in combination with state-of-the-art approaches in oneshot learning.
{"title":"One-Shot Learning of Scene Locations via Feature Trajectory Transfer","authors":"R. Kwitt, S. Hegenbart, M. Niethammer","doi":"10.1109/CVPR.2016.16","DOIUrl":"https://doi.org/10.1109/CVPR.2016.16","url":null,"abstract":"The appearance of (outdoor) scenes changes considerably with the strength of certain transient attributes, such as \"rainy\", \"dark\" or \"sunny\". Obviously, this also affects the representation of an image in feature space, e.g., as activations at a certain CNN layer, and consequently impacts scene recognition performance. In this work, we investigate the variability in these transient attributes as a rich source of information for studying how image representations change as a function of attribute strength. In particular, we leverage a recently introduced dataset with fine-grain annotations to estimate feature trajectories for a collection of transient attributes and then show how these trajectories can be transferred to new image representations. This enables us to synthesize new data along the transferred trajectories with respect to the dimensions of the space spanned by the transient attributes. Applicability of this concept is demonstrated on the problem of oneshot recognition of scene locations. We show that data synthesized via feature trajectory transfer considerably boosts recognition performance, (1) with respect to baselines and (2) in combination with state-of-the-art approaches in oneshot learning.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"61 40 1","pages":"78-86"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90789944","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}
Chuang Gan, Ting Yao, Kuiyuan Yang, Yi Yang, Tao Mei
Video concept learning often requires a large set oftraining samples. In practice, however, acquiring noise-free training labels with sufficient positive examples is very expensive. A plausible solution for training data collection is by sampling from the vast quantities of images and videos on the Web. Such a solution is motivated by the assumption that the retrieved images or videos are highly correlated with the query. Still, a number ofchallenges remain. First, Web videos are often untrimmed. Thus, only parts of the videos are relevant to the query. Second, the retrieved Web images are always highly relevant to the issued query. However, thoughtlessly utilizing the images in the video domain may even hurt the performance due to the well-known semantic drift and domain gap problems. As a result, a valid question is how Web images and videos interact for video concept learning. In this paper, we propose a Lead-Exceed Neural Network (LENN), which reinforces the training on Web images and videos in a curriculum manner. Specifically, the training proceeds by inputting frames of Web videos to obtain a network. The Web images are then filtered by the learnt network and the selected images are additionally fed into the network to enhance the architecture and further trim the videos. In addition, Long Short-Term Memory (LSTM) can be applied on the trimmed videos to explore temporal information. Encouraging results are reported on UCFIOl, TRECVID 2013 and 2014 MEDTest in the context ofboth action recognition and event detection. Without using human annotated exemplars, our proposed LENN can achieve 74.4% accuracy on UCFIOI dataset.
{"title":"You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images","authors":"Chuang Gan, Ting Yao, Kuiyuan Yang, Yi Yang, Tao Mei","doi":"10.1109/CVPR.2016.106","DOIUrl":"https://doi.org/10.1109/CVPR.2016.106","url":null,"abstract":"Video concept learning often requires a large set oftraining samples. In practice, however, acquiring noise-free training labels with sufficient positive examples is very expensive. A plausible solution for training data collection is by sampling from the vast quantities of images and videos on the Web. Such a solution is motivated by the assumption that the retrieved images or videos are highly correlated with the query. Still, a number ofchallenges remain. First, Web videos are often untrimmed. Thus, only parts of the videos are relevant to the query. Second, the retrieved Web images are always highly relevant to the issued query. However, thoughtlessly utilizing the images in the video domain may even hurt the performance due to the well-known semantic drift and domain gap problems. As a result, a valid question is how Web images and videos interact for video concept learning. In this paper, we propose a Lead-Exceed Neural Network (LENN), which reinforces the training on Web images and videos in a curriculum manner. Specifically, the training proceeds by inputting frames of Web videos to obtain a network. The Web images are then filtered by the learnt network and the selected images are additionally fed into the network to enhance the architecture and further trim the videos. In addition, Long Short-Term Memory (LSTM) can be applied on the trimmed videos to explore temporal information. Encouraging results are reported on UCFIOl, TRECVID 2013 and 2014 MEDTest in the context ofboth action recognition and event detection. Without using human annotated exemplars, our proposed LENN can achieve 74.4% accuracy on UCFIOI dataset.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"49 1","pages":"923-932"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90992724","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}
Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.
{"title":"In Defense of Sparse Tracking: Circulant Sparse Tracker","authors":"Tianzhu Zhang, Adel Bibi, Bernard Ghanem","doi":"10.1109/CVPR.2016.421","DOIUrl":"https://doi.org/10.1109/CVPR.2016.421","url":null,"abstract":"Sparse representation has been introduced to visual tracking by finding the best target candidate with minimal reconstruction error within the particle filter framework. However, most sparse representation based trackers have high computational cost, less than promising tracking performance, and limited feature representation. To deal with the above issues, we propose a novel circulant sparse tracker (CST), which exploits circulant target templates. Because of the circulant structure property, CST has the following advantages: (1) It can refine and reduce particles using circular shifts of target templates. (2) The optimization can be efficiently solved entirely in the Fourier domain. (3) High dimensional features can be embedded into CST to significantly improve tracking performance without sacrificing much computation time. Both qualitative and quantitative evaluations on challenging benchmark sequences demonstrate that CST performs better than all other sparse trackers and favorably against state-of-the-art methods.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"8 1","pages":"3880-3888"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79049555","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}
E. Stumm, Christopher Mei, S. Lacroix, Juan I. Nieto, M. Hutter, R. Siegwart
A novel method for visual place recognition is introduced and evaluated, demonstrating robustness to perceptual aliasing and observation noise. This is achieved by increasing discrimination through a more structured representation of visual observations. Estimation of observation likelihoods are based on graph kernel formulations, utilizing both the structural and visual information encoded in covisibility graphs. The proposed probabilistic model is able to circumvent the typically difficult and expensive posterior normalization procedure by exploiting the information available in visual observations. Furthermore, the place recognition complexity is independent of the size of the map. Results show improvements over the state-of-theart on a diverse set of both public datasets and novel experiments, highlighting the benefit of the approach.
{"title":"Robust Visual Place Recognition with Graph Kernels","authors":"E. Stumm, Christopher Mei, S. Lacroix, Juan I. Nieto, M. Hutter, R. Siegwart","doi":"10.1109/CVPR.2016.491","DOIUrl":"https://doi.org/10.1109/CVPR.2016.491","url":null,"abstract":"A novel method for visual place recognition is introduced and evaluated, demonstrating robustness to perceptual aliasing and observation noise. This is achieved by increasing discrimination through a more structured representation of visual observations. Estimation of observation likelihoods are based on graph kernel formulations, utilizing both the structural and visual information encoded in covisibility graphs. The proposed probabilistic model is able to circumvent the typically difficult and expensive posterior normalization procedure by exploiting the information available in visual observations. Furthermore, the place recognition complexity is independent of the size of the map. Results show improvements over the state-of-theart on a diverse set of both public datasets and novel experiments, highlighting the benefit of the approach.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"117 1","pages":"4535-4544"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79965919","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}
Large-pose face alignment is a very challenging problem in computer vision, which is used as a prerequisite for many important vision tasks, e.g, face recognition and 3D face reconstruction. Recently, there have been a few attempts to solve this problem, but still more research is needed to achieve highly accurate results. In this paper, we propose a face alignment method for large-pose face images, by combining the powerful cascaded CNN regressor method and 3DMM. We formulate the face alignment as a 3DMM fitting problem, where the camera projection matrix and 3D shape parameters are estimated by a cascade of CNN-based regressors. The dense 3D shape allows us to design pose-invariant appearance features for effective CNN learning. Extensive experiments are conducted on the challenging databases (AFLW and AFW), with comparison to the state of the art.
{"title":"Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting","authors":"Amin Jourabloo, Xiaoming Liu","doi":"10.1109/CVPR.2016.454","DOIUrl":"https://doi.org/10.1109/CVPR.2016.454","url":null,"abstract":"Large-pose face alignment is a very challenging problem in computer vision, which is used as a prerequisite for many important vision tasks, e.g, face recognition and 3D face reconstruction. Recently, there have been a few attempts to solve this problem, but still more research is needed to achieve highly accurate results. In this paper, we propose a face alignment method for large-pose face images, by combining the powerful cascaded CNN regressor method and 3DMM. We formulate the face alignment as a 3DMM fitting problem, where the camera projection matrix and 3D shape parameters are estimated by a cascade of CNN-based regressors. The dense 3D shape allows us to design pose-invariant appearance features for effective CNN learning. Extensive experiments are conducted on the challenging databases (AFLW and AFW), with comparison to the state of the art.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"3 1","pages":"4188-4196"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88791807","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 method to automatically detect contours, i.e. lines along which the surface orientation sharply changes, in large-scale outdoor point clouds. Contours are important intermediate features for structuring point clouds and converting them into high-quality surface or solid models, and are extensively used in graphics and mapping applications. Yet, detecting them in unstructured, inhomogeneous point clouds turns out to be surprisingly difficult, and existing line detection algorithms largely fail. We approach contour extraction as a two-stage discriminative learning problem. In the first stage, a contour score for each individual point is predicted with a binary classifier, using a set of features extracted from the point's neighborhood. The contour scores serve as a basis to construct an overcomplete graph of candidate contours. The second stage selects an optimal set of contours from the candidates. This amounts to a further binary classification in a higher-order MRF, whose cliques encode a preference for connected contours and penalize loose ends. The method can handle point clouds > 107 points in a couple of minutes, and vastly outperforms a baseline that performs Canny-style edge detection on a range image representation of the point cloud.
{"title":"Contour Detection in Unstructured 3D Point Clouds","authors":"Timo Hackel, J. D. Wegner, K. Schindler","doi":"10.1109/CVPR.2016.178","DOIUrl":"https://doi.org/10.1109/CVPR.2016.178","url":null,"abstract":"We describe a method to automatically detect contours, i.e. lines along which the surface orientation sharply changes, in large-scale outdoor point clouds. Contours are important intermediate features for structuring point clouds and converting them into high-quality surface or solid models, and are extensively used in graphics and mapping applications. Yet, detecting them in unstructured, inhomogeneous point clouds turns out to be surprisingly difficult, and existing line detection algorithms largely fail. We approach contour extraction as a two-stage discriminative learning problem. In the first stage, a contour score for each individual point is predicted with a binary classifier, using a set of features extracted from the point's neighborhood. The contour scores serve as a basis to construct an overcomplete graph of candidate contours. The second stage selects an optimal set of contours from the candidates. This amounts to a further binary classification in a higher-order MRF, whose cliques encode a preference for connected contours and penalize loose ends. The method can handle point clouds > 107 points in a couple of minutes, and vastly outperforms a baseline that performs Canny-style edge detection on a range image representation of the point cloud.","PeriodicalId":6515,"journal":{"name":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"1610-1618"},"PeriodicalIF":0.0,"publicationDate":"2016-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87346556","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：