Raw data of point cloud is often noisy and with topological defects (such as holes), which cause problems including faulty connection and inaccurate structure. As a result, the surface reconstruction of point cloud data is a highly challenging problem. This work proposes a novel method, which improves the surface quality compared with existing methods. Our method combines both the local detailed features and the global topological information during the reconstruction process. To facilitate the feature refinement, we first pre-process the point cloud data by relocating each point, upsampling the point data, and optimizing normals to enhance the features and geometric details. We then identify the topological information by segmenting the geometry and constructing curve skeletons for each part and guide the surface reconstruction with the skeletons by minimal user interaction. We demonstrate the effectiveness of our methods with various examples, where our reconstruction can fill out missing data and preserve sharp features.
{"title":"Feature-Enhanced Surfaces from Incomplete Point Cloud with Segmentation and Curve Skeleton Information","authors":"Meili Wang, Yuling Fan, Shihui Guo, Minghong Liao, Jian Chang, Dongjian He","doi":"10.1109/ICVRV.2017.00027","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00027","url":null,"abstract":"Raw data of point cloud is often noisy and with topological defects (such as holes), which cause problems including faulty connection and inaccurate structure. As a result, the surface reconstruction of point cloud data is a highly challenging problem. This work proposes a novel method, which improves the surface quality compared with existing methods. Our method combines both the local detailed features and the global topological information during the reconstruction process. To facilitate the feature refinement, we first pre-process the point cloud data by relocating each point, upsampling the point data, and optimizing normals to enhance the features and geometric details. We then identify the topological information by segmenting the geometry and constructing curve skeletons for each part and guide the surface reconstruction with the skeletons by minimal user interaction. We demonstrate the effectiveness of our methods with various examples, where our reconstruction can fill out missing data and preserve sharp features.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133049879","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 : 2017-10-01DOI: 10.1109/icvrv.2017.00107
Min Li, Xianjie Yuan
Aiming at the complicated problem of the radiation model in the traditional infrared image simulation and the practical problem that the model usability is difficult to verify, a simulation method of building object infrared image based on guided filtering enhanced feature prediction is proposed. Based on guided filter enhancing feature extraction of the measured images, the images are divided into different regions according to different properties of the material, and the infrared simulation images of the middle time are obtained by feature prediction and fusion. The experimental results show that the infrared enhancement image of the building object which is generated by this algorithm is consistent with the change of the enhanced image, whether it is from the subjective visual effect or the gray histogram. What's more, the algorithm effectively avoids the cumbersome data processing in the general simulation, and has an engineering practical value, low computational complexity, good real-time performance.
{"title":"Building's Infrared Image Simulation Method Based on Guided Filter Enhancing Feature Prediction","authors":"Min Li, Xianjie Yuan","doi":"10.1109/icvrv.2017.00107","DOIUrl":"https://doi.org/10.1109/icvrv.2017.00107","url":null,"abstract":"Aiming at the complicated problem of the radiation model in the traditional infrared image simulation and the practical problem that the model usability is difficult to verify, a simulation method of building object infrared image based on guided filtering enhanced feature prediction is proposed. Based on guided filter enhancing feature extraction of the measured images, the images are divided into different regions according to different properties of the material, and the infrared simulation images of the middle time are obtained by feature prediction and fusion. The experimental results show that the infrared enhancement image of the building object which is generated by this algorithm is consistent with the change of the enhanced image, whether it is from the subjective visual effect or the gray histogram. What's more, the algorithm effectively avoids the cumbersome data processing in the general simulation, and has an engineering practical value, low computational complexity, good real-time performance.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123177254","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00051
Yi Xiao, Chao Pan, Xianyi Zhu, Hai Jiang, Yan Zheng
Inverse halftoning is a kind of technology which transforms binary images composed of black and white pixels to continuous-tone images. Many scholars have studied this problem so far, but the results are not satisfactory. In this paper, we propose an end-to-end deep convolutional neural network composed of two parts. The first part is the feature extraction part which consists of 4 convolution layers and 4 pooling layers to extract feature from the halftoning images. The second part is the reconstruction part which contains 4 deconvolution layers to reconstruct the continuous-tone images. A U-Net structure which concatenates the outputs from the feature extraction layers with deconvolution layers is used for better restoring the detail information of the original images. Experimental results show that our method outperforms the state-of-arts in terms of both visual quality and numerical evaluation
{"title":"Deep Neural Inverse Halftoning","authors":"Yi Xiao, Chao Pan, Xianyi Zhu, Hai Jiang, Yan Zheng","doi":"10.1109/ICVRV.2017.00051","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00051","url":null,"abstract":"Inverse halftoning is a kind of technology which transforms binary images composed of black and white pixels to continuous-tone images. Many scholars have studied this problem so far, but the results are not satisfactory. In this paper, we propose an end-to-end deep convolutional neural network composed of two parts. The first part is the feature extraction part which consists of 4 convolution layers and 4 pooling layers to extract feature from the halftoning images. The second part is the reconstruction part which contains 4 deconvolution layers to reconstruct the continuous-tone images. A U-Net structure which concatenates the outputs from the feature extraction layers with deconvolution layers is used for better restoring the detail information of the original images. Experimental results show that our method outperforms the state-of-arts in terms of both visual quality and numerical evaluation","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127249256","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 : 2017-10-01DOI: 10.1109/icvrv.2017.00059
De-Quan Guo, Sheng-Gui Ling, Peng Sheng, Hong-Yu Yang, L. Hong
To tackle the problem of target scale changed, too monotonous target feature, or track cumulative errors in Kernelized correlation filters(KCF), the paper proposes a self-adaptive KCF tracking algorithm employed multi-feature fusion. KCF tracking algorithm is improved based on location prediction, multi-feature fusion and bilinear interpolation. Among them, to facilitate better representation of the target's appearance model, make target tracking more robust, the multi-feature fusion is integrated (Hue Saturation Value, HSV) color features, grayscale features and improved (Histogram of Oriented Gradient, HOG) features. Both qualitative and quantitative evaluations on some object tracking benchmark show that the proposed tracking method achieves superior performance compared with other state-of-the-art methods.
针对核化相关滤波器(KCF)中目标尺度变化、目标特征过于单调、跟踪误差累积等问题，提出了一种采用多特征融合的自适应KCF跟踪算法。基于位置预测、多特征融合和双线性插值对KCF跟踪算法进行了改进。其中，为了更好地表征目标的外观模型，使目标跟踪更加鲁棒，多特征融合融合了(Hue Saturation Value, HSV)颜色特征、灰度特征和改进的(Histogram of Oriented Gradient, HOG)特征。在一些目标跟踪基准上进行了定性和定量的评价，结果表明该方法的跟踪性能优于其他先进的跟踪方法。
{"title":"An Adaptive KCF Tracking Via Multi-feature Fusion","authors":"De-Quan Guo, Sheng-Gui Ling, Peng Sheng, Hong-Yu Yang, L. Hong","doi":"10.1109/icvrv.2017.00059","DOIUrl":"https://doi.org/10.1109/icvrv.2017.00059","url":null,"abstract":"To tackle the problem of target scale changed, too monotonous target feature, or track cumulative errors in Kernelized correlation filters(KCF), the paper proposes a self-adaptive KCF tracking algorithm employed multi-feature fusion. KCF tracking algorithm is improved based on location prediction, multi-feature fusion and bilinear interpolation. Among them, to facilitate better representation of the target's appearance model, make target tracking more robust, the multi-feature fusion is integrated (Hue Saturation Value, HSV) color features, grayscale features and improved (Histogram of Oriented Gradient, HOG) features. Both qualitative and quantitative evaluations on some object tracking benchmark show that the proposed tracking method achieves superior performance compared with other state-of-the-art methods.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125159137","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00086
Zixin Hu, Yanfen Gan, Jixiang Yang, Junliu Zhong
Nowadays, face the abuse of digital technique, it is much necessary to detect whether a digital image is an original one or artificial modification. In this paper, we proposed an effective image feature extracting and matching scheme for Copy-move forgery detection. First, after pre-processing, the overlapped block is slid one pixel each time to detect the host image. Discrete analytical Fourier-Mellin transform is presented to extract the features in each block. Then, locality sensitive hashing is proposed for distinguishing the identical or similar block features in matching step to get the inlier matches. Finally, the geometric operations are presented to better indicate the detected regions. A series of experimental results indicated that the proposed scheme can identify the forgery images and outperforms the state-of-the-art techniques.
{"title":"An Effective Feature Extracting and Matching Scheme for Copy-Move Forgery Detection","authors":"Zixin Hu, Yanfen Gan, Jixiang Yang, Junliu Zhong","doi":"10.1109/ICVRV.2017.00086","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00086","url":null,"abstract":"Nowadays, face the abuse of digital technique, it is much necessary to detect whether a digital image is an original one or artificial modification. In this paper, we proposed an effective image feature extracting and matching scheme for Copy-move forgery detection. First, after pre-processing, the overlapped block is slid one pixel each time to detect the host image. Discrete analytical Fourier-Mellin transform is presented to extract the features in each block. Then, locality sensitive hashing is proposed for distinguishing the identical or similar block features in matching step to get the inlier matches. Finally, the geometric operations are presented to better indicate the detected regions. A series of experimental results indicated that the proposed scheme can identify the forgery images and outperforms the state-of-the-art techniques.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115097751","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00029
Xincan Zhao, Penglei Zhan, Yaodan Liu
Aiming at the problems of the complex modeling, large amount and variety of data in the 3D modeling of viaducts and underpass tunnels in digital city, a novel approach is proposed for the rapid construction of 3D urban road network based on the two-dimensional raster map. Extract the centerlines of roads from the two dimensional raster map of different layers, then the rapid three-dimensional solid modeling of the viaducts and underpass tunnels could be realized through the parametric modeling and texture mapping. The experimental results show that the proposed parametric modeling approach of the urban road network could greatly reduce the modeling time, and improve the design efficiency with better flexibility and interactivity.
{"title":"Rapid Construction Algorithm of 3D Urban Road Network from Raster Maps","authors":"Xincan Zhao, Penglei Zhan, Yaodan Liu","doi":"10.1109/ICVRV.2017.00029","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00029","url":null,"abstract":"Aiming at the problems of the complex modeling, large amount and variety of data in the 3D modeling of viaducts and underpass tunnels in digital city, a novel approach is proposed for the rapid construction of 3D urban road network based on the two-dimensional raster map. Extract the centerlines of roads from the two dimensional raster map of different layers, then the rapid three-dimensional solid modeling of the viaducts and underpass tunnels could be realized through the parametric modeling and texture mapping. The experimental results show that the proposed parametric modeling approach of the urban road network could greatly reduce the modeling time, and improve the design efficiency with better flexibility and interactivity.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128446695","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00124
Renjie Xu, Fuling Zhang
this paper analysis and summaries the general concepts and classifications of the battlefield particle effects, and realistic implementation based the Cryengine SandBox editor, in order to present the realistic virtual battlefield scenes
{"title":"Battlefield Particle Effects Research","authors":"Renjie Xu, Fuling Zhang","doi":"10.1109/ICVRV.2017.00124","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00124","url":null,"abstract":"this paper analysis and summaries the general concepts and classifications of the battlefield particle effects, and realistic implementation based the Cryengine SandBox editor, in order to present the realistic virtual battlefield scenes","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121577003","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 present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that mechanism contains not only geometric shapes but also internal motion structures which can be calculated to adjust geometric shapes of the mechanical parts. Our system consists of two steps: disassemble mechanical object into a group set and pack them within a box efficiently. The first step is to create a hierarchy of possible group set of parts which is generated by disconnecting the selected joints and adjust motion structures of parts in groups. The aim of this step is seeking total minimum volume of each group. The second step is to exploit the hierarchy based on breadth-first-search to obtain a group set. Every group in the set is inserted into specified box from maximum volume to minimum based on our packing strategy. Until an approximated result with satisfied efficiency is accepted, our approach finish exploiting the hierarchy.
{"title":"Efficiently Disassemble-and-Pack for Mechanism","authors":"Mingyuan Li, Xiaoheng Jiang, N. Gu, Weiwei Xu, Junxiao Xue, Bing Zhou, Mingliang Xu","doi":"10.1109/ICVRV.2017.00031","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00031","url":null,"abstract":"In this paper, we present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that mechanism contains not only geometric shapes but also internal motion structures which can be calculated to adjust geometric shapes of the mechanical parts. Our system consists of two steps: disassemble mechanical object into a group set and pack them within a box efficiently. The first step is to create a hierarchy of possible group set of parts which is generated by disconnecting the selected joints and adjust motion structures of parts in groups. The aim of this step is seeking total minimum volume of each group. The second step is to exploit the hierarchy based on breadth-first-search to obtain a group set. Every group in the set is inserted into specified box from maximum volume to minimum based on our packing strategy. Until an approximated result with satisfied efficiency is accepted, our approach finish exploiting the hierarchy.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113983472","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00091
Rui Han, Zhiquan Feng, Tao Xu, Changsheng Ai, We Xie, Kai Zhang, Jianxin Li
Human-computer interaction, especially gesturebased interactive technology, plays an important role in virtual reality scenarios. Currently, gesture-based interactive technology mostly uses a single sensor, such as data gloves or Kinect. When using single data gloves, some have the problem of lacking hand displacement information. When using single Kinect, it can't be real-time and intuitive to show the changes in gestures. And when the gestures are blocked, the gesture recognition rate drops. Therefore, multi-sensors based 3D gesture recognition and interaction method is proposed. To achieve the 3D gesture visualization, tracking and recognition. Experiments show the effectiveness of the proposed method. It can overcome the shortcomings of a single sensor.
{"title":"Multi-sensors Based 3D Gesture Recognition and Interaction in Virtual Block Game","authors":"Rui Han, Zhiquan Feng, Tao Xu, Changsheng Ai, We Xie, Kai Zhang, Jianxin Li","doi":"10.1109/ICVRV.2017.00091","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00091","url":null,"abstract":"Human-computer interaction, especially gesturebased interactive technology, plays an important role in virtual reality scenarios. Currently, gesture-based interactive technology mostly uses a single sensor, such as data gloves or Kinect. When using single data gloves, some have the problem of lacking hand displacement information. When using single Kinect, it can't be real-time and intuitive to show the changes in gestures. And when the gestures are blocked, the gesture recognition rate drops. Therefore, multi-sensors based 3D gesture recognition and interaction method is proposed. To achieve the 3D gesture visualization, tracking and recognition. Experiments show the effectiveness of the proposed method. It can overcome the shortcomings of a single sensor.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114837770","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}
Planar parameterization of triangulated surface meshes is used to find an isomorphic mapping between a discrete 3D surface and a planar patch, a crucial problem in computer graphics, computer aided design and digital geometric processing. This paper introduces an algorithm for parameterizing 3D meshes by minimizing the angle and area distortion energy. The parameterization algorithm traverses the mesh in a region growing way and is able to yield results with less global distortion. Various applications are tested to illustrate the effectiveness of the techniques proposed in this paper.
{"title":"Conformal Parameterization by Minimizing Distortion Energy","authors":"Junxiao Xue, Zekun Wang, Chengming Liu, Mingliang Xu","doi":"10.1109/ICVRV.2017.00020","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00020","url":null,"abstract":"Planar parameterization of triangulated surface meshes is used to find an isomorphic mapping between a discrete 3D surface and a planar patch, a crucial problem in computer graphics, computer aided design and digital geometric processing. This paper introduces an algorithm for parameterizing 3D meshes by minimizing the angle and area distortion energy. The parameterization algorithm traverses the mesh in a region growing way and is able to yield results with less global distortion. Various applications are tested to illustrate the effectiveness of the techniques proposed in this paper.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117053419","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：