2016 Fourth International Conference on 3D Vision (3DV)最新文献_第3页

Shape Analysis with Anisotropic Windowed Fourier Transform 基于各向异性加窗傅里叶变换的形状分析

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.57

S. Melzi, E. Rodolà, U. Castellani, M. Bronstein

引用次数: 19

A 3D Reconstruction with High Density and Accuracy Using Laser Profiler and Camera Fusion System on a Rover 利用激光剖面仪和相机融合系统在火星车上进行高密度、高精度的三维重建

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.70

Ryoichi Ishikawa, Menandro Roxas, Yoshihiro Sato, Takeshi Oishi, T. Masuda, K. Ikeuchi

引用次数: 7

HS-Nets: Estimating Human Body Shape from Silhouettes with Convolutional Neural Networks HS-Nets:用卷积神经网络从轮廓估计人体形状

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.19

E. Dibra, H. Jain, Cengiz Oztireli, R. Ziegler, M. Gross

引用次数: 81

Point Cloud Noise and Outlier Removal for Image-Based 3D Reconstruction 基于图像的三维重建中的点云噪声和离群值去除

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.20

Katja Wolff, Changil Kim, H. Zimmer, Christopher Schroers, M. Botsch, O. Sorkine-Hornung, A. Sorkine-Hornung

引用次数: 89

Energy-Based Global Ternary Image for Action Recognition Using Sole Depth Sequences 基于能量的全局三元图像单一深度序列动作识别

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.14

Mengyuan Liu, Hong Liu, Chen Chen, M. Najafian

{"title":"Energy-Based Global Ternary Image for Action Recognition Using Sole Depth Sequences","authors":"Mengyuan Liu, Hong Liu, Chen Chen, M. Najafian","doi":"10.1109/3DV.2016.14","DOIUrl":"https://doi.org/10.1109/3DV.2016.14","url":null,"abstract":"In order to efficiently recognize actions from depth sequences, we propose a novel feature, called Global Ternary Image (GTI), which implicitly encodes both motion regions and motion directions between consecutive depth frames via recording the changes of depth pixels. In this study, each pixel in GTI indicates one of the three possible states, namely positive, negative and neutral, which represents increased, decreased and same depth values, respectively. Since GTI is sensitive to the subject's speed, we obtain energy-based GTI (E-GTI) by extracting GTI from pairwise depth frames with equal motion energy. To involve temporal information among depth frames, we extract E-GTI using multiple settings of motion energy. Here, the noise can be effectively suppressed by describing E-GTIs using the Radon Transform (RT). The 3D action representation is formed as a result of feeding the hierarchical combination of RTs to the Bag of Visual Words model (BoVW). From the extensive experiments on four benchmark datasets, namely MSRAction3D, DHA, MSRGesture3D and SKIG, it is evident that the hierarchical E-GTI outperforms the existing methods in 3D action recognition. We tested our proposed approach on extended MSRAction3D dataset to further investigate and verify its robustness against partial occlusions, noise and speed.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"181 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":"122456361","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}

引用次数: 12

A Hybrid Structure/Trajectory Constraint for Visual SLAM 视觉SLAM的混合结构/轨迹约束

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.12

Angélique Loesch, S. Bourgeois, V. Gay-Bellile, M. Dhome

引用次数: 2

Robust Real-Time 3D Face Tracking from RGBD Videos under Extreme Pose, Depth, and Expression Variation 基于极端姿态、深度和表情变化的RGBD视频鲁棒实时3D人脸跟踪

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.54

Hai Xuan Pham, V. Pavlovic

{"title":"Robust Real-Time 3D Face Tracking from RGBD Videos under Extreme Pose, Depth, and Expression Variation","authors":"Hai Xuan Pham, V. Pavlovic","doi":"10.1109/3DV.2016.54","DOIUrl":"https://doi.org/10.1109/3DV.2016.54","url":null,"abstract":"We introduce a novel end-to-end real-time pose-robust 3D face tracking framework from RGBD videos, which is capable of tracking head pose and facial actions simultaneously in unconstrained environment without intervention or pre-calibration from a user. In particular, we emphasize tracking the head pose from profile to profile and improving tracking performance in challenging instances, where the tracked subject is at a considerably large distance from the camera and the quality of data deteriorates severely. To achieve these goals, the tracker is guided by an efficient multi-view 3D shape regressor, trained upon generic RGB datasets, which is able to predict model parameters despite large head rotations or tracking range. Specifically, the shape regressor is made aware of the head pose by inferring the possibility of particular facial landmarks being visible through a joint regression-classification local random forest framework, and piecewise linear regression models effectively map visibility features into shape parameters. In addition, the regressor is combined with a joint 2D+3D optimization that sparsely exploits depth information to further refine shape parameters to maintain tracking accuracy over time. The result is a robust on-line RGBD 3D face tracker that can model extreme head poses and facial expressions accurately in challenging scenes, which are demonstrated in our extensive experiments.","PeriodicalId":425304,"journal":{"name":"2016 Fourth International Conference on 3D Vision (3DV)","volume":"458 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":"125831852","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}

引用次数: 9

CNN-Based Object Segmentation in Urban LIDAR with Missing Points 基于cnn的城市激光雷达缺点目标分割

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.51

Allan Zelener, I. Stamos

引用次数: 19

Matching Deformable Objects in Clutter 在杂乱中匹配可变形物体

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.10

L. Cosmo, E. Rodolà, Jonathan Masci, A. Torsello, M. Bronstein

引用次数: 55

Comparison of Radial and Tangential Geometries for Cylindrical Panorama 圆柱全景的径向几何和切向几何的比较

2016 Fourth International Conference on 3D Vision (3DV) Pub Date : 2016-10-01 DOI: 10.1109/3DV.2016.81

F. Amjadi, S. Roy

引用次数: 1