This work proposes a method bridging the existing gap between progressive sparse 3D reconstruction (incremental Structure from Motion) and progressive point based dense 3D reconstruction (Multi-View Stereo). The presented algorithm is capable of adapting an existing dense 3D model to changes such as the addition or removal of new images, the merge of scene parts, or changes in the underlying camera calibration. The existing 3D model is transformed as consistently as possible and the structure is reused as much as possible without sacrificing the accuracy and/or completeness of the final result. A significant decrease in runtime is achieved compared to the re-computation of a new dense point cloud from scratch. We demonstrate the performance of the algorithm in various experiments on publicly available datasets of different sizes and compare it to the baseline. The work interacts seamlessly with publicly available software enabling an integrated progressive 3D modeling pipeline.
{"title":"Progressive 3D Modeling All the Way","authors":"Alex Locher, M. Havlena, L. Gool","doi":"10.1109/3DV.2016.11","DOIUrl":"https://doi.org/10.1109/3DV.2016.11","url":null,"abstract":"This work proposes a method bridging the existing gap between progressive sparse 3D reconstruction (incremental Structure from Motion) and progressive point based dense 3D reconstruction (Multi-View Stereo). The presented algorithm is capable of adapting an existing dense 3D model to changes such as the addition or removal of new images, the merge of scene parts, or changes in the underlying camera calibration. The existing 3D model is transformed as consistently as possible and the structure is reused as much as possible without sacrificing the accuracy and/or completeness of the final result. A significant decrease in runtime is achieved compared to the re-computation of a new dense point cloud from scratch. We demonstrate the performance of the algorithm in various experiments on publicly available datasets of different sizes and compare it to the baseline. The work interacts seamlessly with publicly available software enabling an integrated progressive 3D modeling pipeline.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233795","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}
Stereo matching is a popular technique to infer depth from two or more images and wealth of methods have been proposed to deal with this problem. Despite these efforts, finding accurate stereo correspondences is still an open problem. The strengths and weaknesses of existing methods are often complementary and in this paper, motivated by recent trends in this field, we exploit this fact by proposing Deep Stereo Fusion, a Convolutional Neural Network capable of combining the output of multiple stereo algorithms in order to obtain more accurate result with respect to each input disparity map. Deep Stereo Fusion process a 3D features vector, encoding both spatial and cross-algorithm information, in order to select the best disparity hypothesis among those proposed by the single stereo matchers. To the best of our knowledge, our proposal is the first i) to leverage on deep learning and ii) able to predict the optimal disparity assignments by taking only as input cue the disparity maps. This second feature makes our method suitable for deployment even when other cues (e.g., confidence) are not available such as when dealing with disparity maps provided by off-the-shelf 3D sensors. We thoroughly evaluate our proposal on the KITTI stereo benchmark with respect state-of-the-art in this field.
{"title":"Deep Stereo Fusion: Combining Multiple Disparity Hypotheses with Deep-Learning","authors":"Matteo Poggi, S. Mattoccia","doi":"10.1109/3DV.2016.22","DOIUrl":"https://doi.org/10.1109/3DV.2016.22","url":null,"abstract":"Stereo matching is a popular technique to infer depth from two or more images and wealth of methods have been proposed to deal with this problem. Despite these efforts, finding accurate stereo correspondences is still an open problem. The strengths and weaknesses of existing methods are often complementary and in this paper, motivated by recent trends in this field, we exploit this fact by proposing Deep Stereo Fusion, a Convolutional Neural Network capable of combining the output of multiple stereo algorithms in order to obtain more accurate result with respect to each input disparity map. Deep Stereo Fusion process a 3D features vector, encoding both spatial and cross-algorithm information, in order to select the best disparity hypothesis among those proposed by the single stereo matchers. To the best of our knowledge, our proposal is the first i) to leverage on deep learning and ii) able to predict the optimal disparity assignments by taking only as input cue the disparity maps. This second feature makes our method suitable for deployment even when other cues (e.g., confidence) are not available such as when dealing with disparity maps provided by off-the-shelf 3D sensors. We thoroughly evaluate our proposal on the KITTI stereo benchmark with respect state-of-the-art in this field.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122213297","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}
Many compelling video post-processing effects, in particular aesthetic focus editing and refocusing effects, are feasible if per-frame depth information is available. Existing computational methods to capture RGB and depth either purposefully modify the optics (coded aperture, light-field imaging), or employ active RGB-D cameras. Since these methods are less practical for users with normal cameras, we present an algorithm to capture all-in-focus RGB-D video of dynamic scenes with an unmodified commodity video camera. Our algorithm turns the often unwanted defocus blur into a valuable signal. The input to our method is a video in which the focus plane is continuously moving back and forth during capture, and thus defocus blur is provoked and strongly visible. This can be achieved by manually turning the focus ring of the lens during recording. The core algorithmic ingredient is a new video-based depth-from-defocus algorithm that computes space-time-coherent depth maps, deblurred all-in-focus video, and the focus distance for each frame. We extensively evaluate our approach, and show that it enables compelling video post-processing effects, such as different types of refocusing.
{"title":"Video Depth-from-Defocus","authors":"Hyeongwoo Kim, Christian Richardt, C. Theobalt","doi":"10.1109/3DV.2016.46","DOIUrl":"https://doi.org/10.1109/3DV.2016.46","url":null,"abstract":"Many compelling video post-processing effects, in particular aesthetic focus editing and refocusing effects, are feasible if per-frame depth information is available. Existing computational methods to capture RGB and depth either purposefully modify the optics (coded aperture, light-field imaging), or employ active RGB-D cameras. Since these methods are less practical for users with normal cameras, we present an algorithm to capture all-in-focus RGB-D video of dynamic scenes with an unmodified commodity video camera. Our algorithm turns the often unwanted defocus blur into a valuable signal. The input to our method is a video in which the focus plane is continuously moving back and forth during capture, and thus defocus blur is provoked and strongly visible. This can be achieved by manually turning the focus ring of the lens during recording. The core algorithmic ingredient is a new video-based depth-from-defocus algorithm that computes space-time-coherent depth maps, deblurred all-in-focus video, and the focus distance for each frame. We extensively evaluate our approach, and show that it enables compelling video post-processing effects, such as different types of refocusing.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130078926","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 for 3D tracking of deformable surfaces with dynamic topology, for instance a paper that undergoes cutting or tearing. Existing template-based methods assume a template of fixed topology. Thus, they fail in tracking deformable objects that undergo topological changes. In our work, we employ a dynamic template (3D mesh) whose topology evolves based on the topological changes of the observed geometry. Our tracking framework deforms the defined template based on three types of constraints: (a) the surface of the template has to be registered to the 3D shape of the tracked surface, (b) the template deformation should respect feature (SIFT) correspondences between selected pairs of frames, and (c) the lengths of the template edges should be preserved. The latter constraint is relaxed when an edge is found to lie on a "geometric gap", that is, when a significant depth discontinuity is detected along this edge. The topology of the template is updated on the fly by removing overstretched edges that lie on a geometric gap. The proposed method has been evaluated quantitatively and qualitatively in both synthetic and real sequences of monocular RGB-D views of surfaces that undergo various types of topological changes. The obtained results show that our approach tracks effectively objects with evolving topology and outperforms state of the art methods in tracking accuracy.
{"title":"Tracking Deformable Surfaces That Undergo Topological Changes Using an RGB-D Camera","authors":"Aggeliki Tsoli, Antonis A. Argyros","doi":"10.1109/3DV.2016.42","DOIUrl":"https://doi.org/10.1109/3DV.2016.42","url":null,"abstract":"We present a method for 3D tracking of deformable surfaces with dynamic topology, for instance a paper that undergoes cutting or tearing. Existing template-based methods assume a template of fixed topology. Thus, they fail in tracking deformable objects that undergo topological changes. In our work, we employ a dynamic template (3D mesh) whose topology evolves based on the topological changes of the observed geometry. Our tracking framework deforms the defined template based on three types of constraints: (a) the surface of the template has to be registered to the 3D shape of the tracked surface, (b) the template deformation should respect feature (SIFT) correspondences between selected pairs of frames, and (c) the lengths of the template edges should be preserved. The latter constraint is relaxed when an edge is found to lie on a \"geometric gap\", that is, when a significant depth discontinuity is detected along this edge. The topology of the template is updated on the fly by removing overstretched edges that lie on a geometric gap. The proposed method has been evaluated quantitatively and qualitatively in both synthetic and real sequences of monocular RGB-D views of surfaces that undergo various types of topological changes. The obtained results show that our approach tracks effectively objects with evolving topology and outperforms state of the art methods in tracking accuracy.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129798439","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}
Classical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of the desired map when applied to some input data. Such formulations are typically one-sided - they seek for a mapping from one shape to the other, but not vice versa. In this paper we consider an unbiased formulation of this problem, in which we solve simultaneously for a low-distortion map relating the two given shapes and its inverse. We phrase the problem in the spectral domain using the language of functional maps, resulting in an especially compact and efficient optimization problem. The benefits of our proposed regularization are especially evident in the scarce data setting, where we demonstrate highly competitive results with respect to the state of the art.
{"title":"Coupled Functional Maps","authors":"D. Eynard, E. Rodolà, K. Glashoff, M. Bronstein","doi":"10.1109/3DV.2016.49","DOIUrl":"https://doi.org/10.1109/3DV.2016.49","url":null,"abstract":"Classical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of the desired map when applied to some input data. Such formulations are typically one-sided - they seek for a mapping from one shape to the other, but not vice versa. In this paper we consider an unbiased formulation of this problem, in which we solve simultaneously for a low-distortion map relating the two given shapes and its inverse. We phrase the problem in the spectral domain using the language of functional maps, resulting in an especially compact and efficient optimization problem. The benefits of our proposed regularization are especially evident in the scarce data setting, where we demonstrate highly competitive results with respect to the state of the art.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124233666","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 new mathematical framework for multi-view surface reconstruction from a set of calibrated color and depth images. We estimate the occupancy probability of points in space along sight rays, and combine these estimates using a normalized product derived from Bayes' rule. The advantage of this approach is that the free space constraint is a natural consequence of the formulation, and not a separate logical operation. We present a single closed form implicit expression for the reconstructed surface in terms of the image data and camera projections, making analytic properties such as surface normals not only easy to compute, but exact. This expression can be efficiently evaluated on the GPU, making it ideal for high performance real-time applications, such as live human body capture for immersive telepresence.
{"title":"A Closed-Form Bayesian Fusion Equation Using Occupancy Probabilities","authors":"Charles T. Loop, Q. Cai, Sergio Orts, P. Chou","doi":"10.1109/3DV.2016.47","DOIUrl":"https://doi.org/10.1109/3DV.2016.47","url":null,"abstract":"We present a new mathematical framework for multi-view surface reconstruction from a set of calibrated color and depth images. We estimate the occupancy probability of points in space along sight rays, and combine these estimates using a normalized product derived from Bayes' rule. The advantage of this approach is that the free space constraint is a natural consequence of the formulation, and not a separate logical operation. We present a single closed form implicit expression for the reconstructed surface in terms of the image data and camera projections, making analytic properties such as surface normals not only easy to compute, but exact. This expression can be efficiently evaluated on the GPU, making it ideal for high performance real-time applications, such as live human body capture for immersive telepresence.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123026394","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 propose a deep convolutional neural network for 3D human pose and camera estimation from monocular images that learns from 2D joint annotations. The proposed network follows the typical architecture, but contains an additional output layer which projects predicted 3D joints onto 2D, and enforces constraints on body part lengths in 3D. We further enforce pose constraints using an independently trained network that learns a prior distribution over 3D poses. We evaluate our approach on several benchmark datasets and compare against state-of-the-art approaches for 3D human pose estimation, achieving comparable performance. Additionally, we show that our approach significantly outperforms other methods in cases where 3D ground truth data is unavailable, and that our network exhibits good generalization properties.
{"title":"3D Human Pose Estimation via Deep Learning from 2D Annotations","authors":"Ernesto Brau, Hao Jiang","doi":"10.1109/3DV.2016.84","DOIUrl":"https://doi.org/10.1109/3DV.2016.84","url":null,"abstract":"We propose a deep convolutional neural network for 3D human pose and camera estimation from monocular images that learns from 2D joint annotations. The proposed network follows the typical architecture, but contains an additional output layer which projects predicted 3D joints onto 2D, and enforces constraints on body part lengths in 3D. We further enforce pose constraints using an independently trained network that learns a prior distribution over 3D poses. We evaluate our approach on several benchmark datasets and compare against state-of-the-art approaches for 3D human pose estimation, achieving comparable performance. Additionally, we show that our approach significantly outperforms other methods in cases where 3D ground truth data is unavailable, and that our network exhibits good generalization properties.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115335423","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 : 2016-10-01DOI: 10.3929/ETHZ-A-010819535
Marcin Dymczyk, E. Stumm, Juan I. Nieto, R. Siegwart, Igor Gilitschenski
An increasing number of simultaneous localization and mapping (SLAM) systems are using appearance-based localization to improve the quality of pose estimates. However, with the growing time-spans and size of the areas we want to cover, appearance-based maps are often becoming too large to handle and are consisting of features that are not always reliable for localization purposes. This paper presents a method for selecting map features that are persistent over time and thus suited for long-term localization. Our methodology relies on a CNN classifier based on image patches and depth maps for recognizing which features are suitable for life-long matchability. Thus, the classifier not only considers the appearance of a feature but also takes into account its expected lifetime. As a result, our feature selection approach produces more compact maps with a high fraction of temporally-stable features compared to the current state-of-the-art, while rejecting unstable features that typically harm localization. Our approach is validated on indoor and outdoor datasets, that span over a period of several months.
{"title":"Will It Last? Learning Stable Features for Long-Term Visual Localization","authors":"Marcin Dymczyk, E. Stumm, Juan I. Nieto, R. Siegwart, Igor Gilitschenski","doi":"10.3929/ETHZ-A-010819535","DOIUrl":"https://doi.org/10.3929/ETHZ-A-010819535","url":null,"abstract":"An increasing number of simultaneous localization and mapping (SLAM) systems are using appearance-based localization to improve the quality of pose estimates. However, with the growing time-spans and size of the areas we want to cover, appearance-based maps are often becoming too large to handle and are consisting of features that are not always reliable for localization purposes. This paper presents a method for selecting map features that are persistent over time and thus suited for long-term localization. Our methodology relies on a CNN classifier based on image patches and depth maps for recognizing which features are suitable for life-long matchability. Thus, the classifier not only considers the appearance of a feature but also takes into account its expected lifetime. As a result, our feature selection approach produces more compact maps with a high fraction of temporally-stable features compared to the current state-of-the-art, while rejecting unstable features that typically harm localization. Our approach is validated on indoor and outdoor datasets, that span over a period of several months.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131122540","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}
Binh-Son Hua, Quang-Hieu Pham, D. Nguyen, Minh-Khoi Tran, L. Yu, Sai-Kit Yeung
Several RGB-D datasets have been publicized over the past few years for facilitating research in computer vision and robotics. However, the lack of comprehensive and fine-grained annotation in these RGB-D datasets has posed challenges to their widespread usage. In this paper, we introduce SceneNN, an RGB-D scene dataset consisting of 100 scenes. All scenes are reconstructed into triangle meshes and have per-vertex and per-pixel annotation. We further enriched the dataset with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses. We used the dataset as a benchmark to evaluate the state-of-the-art methods on relevant research problems such as intrinsic decomposition and shape completion. Our dataset and annotation tools are available at http://www.scenenn.net.
{"title":"SceneNN: A Scene Meshes Dataset with aNNotations","authors":"Binh-Son Hua, Quang-Hieu Pham, D. Nguyen, Minh-Khoi Tran, L. Yu, Sai-Kit Yeung","doi":"10.1109/3DV.2016.18","DOIUrl":"https://doi.org/10.1109/3DV.2016.18","url":null,"abstract":"Several RGB-D datasets have been publicized over the past few years for facilitating research in computer vision and robotics. However, the lack of comprehensive and fine-grained annotation in these RGB-D datasets has posed challenges to their widespread usage. In this paper, we introduce SceneNN, an RGB-D scene dataset consisting of 100 scenes. All scenes are reconstructed into triangle meshes and have per-vertex and per-pixel annotation. We further enriched the dataset with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses. We used the dataset as a benchmark to evaluate the state-of-the-art methods on relevant research problems such as intrinsic decomposition and shape completion. Our dataset and annotation tools are available at http://www.scenenn.net.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121681100","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 design a novel planar 2D fiducial marker and develop fast detection algorithm aiming easy camera calibration and precise 3D reconstruction at the marker locations via the bundle adjustment. Even though an abundance of planar fiducial markers have been made and used in various tasks, none of them has properties necessary to solve the aforementioned tasks. Our marker, X-tag, enjoys a novel design, coupled with very efficient and robust detection scheme, resulting in a reduced number of false positives. This is achieved by constructing markers with random circular features in the image domain and encoding them using two true perspective invariants: cross-ratios and intersection preservation constraints. To detect the markers, we developed an effective search scheme, similar to Geometric Hashing and Hough Voting, in which the marker decoding is cast as a retrieval problem. We apply our system to the task of camera calibration and bundle adjustment. With qualitative and quantitative experiments, we demonstrate the robustness and accuracy of X-tag in spite of blur, noise, perspective and radial distortions, and showcase camera calibration, bundle adjustment and 3d fusion of depth data from precise extrinsic camera poses.
{"title":"X-Tag: A Fiducial Tag for Flexible and Accurate Bundle Adjustment","authors":"Tolga Birdal, Ievgeniia Dobryden, Slobodan Ilic","doi":"10.1109/3DV.2016.65","DOIUrl":"https://doi.org/10.1109/3DV.2016.65","url":null,"abstract":"In this paper we design a novel planar 2D fiducial marker and develop fast detection algorithm aiming easy camera calibration and precise 3D reconstruction at the marker locations via the bundle adjustment. Even though an abundance of planar fiducial markers have been made and used in various tasks, none of them has properties necessary to solve the aforementioned tasks. Our marker, X-tag, enjoys a novel design, coupled with very efficient and robust detection scheme, resulting in a reduced number of false positives. This is achieved by constructing markers with random circular features in the image domain and encoding them using two true perspective invariants: cross-ratios and intersection preservation constraints. To detect the markers, we developed an effective search scheme, similar to Geometric Hashing and Hough Voting, in which the marker decoding is cast as a retrieval problem. We apply our system to the task of camera calibration and bundle adjustment. With qualitative and quantitative experiments, we demonstrate the robustness and accuracy of X-tag in spite of blur, noise, perspective and radial distortions, and showcase camera calibration, bundle adjustment and 3d fusion of depth data from precise extrinsic camera poses.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123982928","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：