3D 视觉 - arXivDaily 专题

1808.00671 2019-09-30 cs.CV cs.RO 62%

PCN: Point Completion Network

Wentao Yuan, Tejas Khot, David Held, Christoph Mertz, Martial Hebert

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 3DV 2018 oral. Honorable mention for Best Paper award

1909.05483 2019-09-13 cs.CV cs.GR 62%

3D Ken Burns Effect from a Single Image

Simon Niklaus, Long Mai, Jimei Yang, Feng Liu

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Comments TOG 2019, http://sniklaus.com/kenburns

1909.04163 2019-09-11 cs.CV cs.LG cs.RO 62%

MLOD: A multi-view 3D object detection based on robust feature fusion method

Jian Deng, Krzysztof Czarnecki

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 6 pages, 6 figures, 2019 22st International Conference on Intelligent Transportation Systems (ITSC)

1909.03462 2019-09-10 cs.CV cs.LG cs.RO 62%

Deep Workpiece Region Segmentation for Bin Picking

Muhammad Usman Khalid, Janik M. Hager, Werner Kraus, Marco F. Huber, Marc Toussaint

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments IEEE CASE 2019

1905.10520 2019-08-20 cs.CV cs.RO 62%

6-DOF GraspNet: Variational Grasp Generation for Object Manipulation

Arsalan Mousavian, Clemens Eppner, Dieter Fox

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to ICCV 2019. Extended camera ready version with additional experiments

1904.01416 2019-08-19 cs.CV cs.RO 62%

SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

Jens Behley, Martin Garbade, Andres Milioto, Jan Quenzel, Sven Behnke, Cyrill Stachniss, Juergen Gall

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments ICCV2019. See teaser video at http://bit.ly/SemanticKITTI-teaser

1908.01504 2019-08-06 cs.CV cs.RO 62%

Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

Weilin Wan, Aaron Walsman, Dieter Fox

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Journal ref IEEE International Conference on Robotics and Automation 2019

1803.08181 2019-08-06 cs.RO cs.CV 62%

CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks

Ganesh Iyer, R. Karnik Ram., J. Krishna Murthy, K. Madhava Krishna

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Appeared in the proccedings of the IEEE International Conference on Intelligent Robots and Systems (IROS) 2018

1906.00208 2019-07-18 cs.CV cs.AI cs.LG cs.RO 62%

RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving

Khaled El Madawy, Hazem Rashed, Ahmad El Sallab, Omar Nasr, Hanan Kamel, Senthil Yogamani

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for Oral Presentation at IEEE Intelligent Transportation Systems Conference (ITSC) 2019

1907.04057 2019-07-11 cs.RO cs.CV eess.IV 62%

Lidar-based Object Classification with Explicit Occlusion Modeling

Xiaoxiang Zhang, Hao Fu, Bin Dai

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1707.00893 2019-07-02 cs.RO cs.CV cs.LG 62%

Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

Philipp Jund, Andreas Eitel, Nichola Abdo, Wolfram Burgard

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for publication at ICRA2018. Supplementary Video: http://spatialrelations.cs.uni-freiburg.de/

1906.11873 2019-07-01 cs.CV cs.LG cs.RO eess.IV 62%

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

Hager Radi, Waleed Ali

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted at Thirty-sixth International Conference on Machine Learning (ICML 2019) Workshop on AI for Autonomous Driving

1906.11435 2019-07-01 cs.RO cs.CV 62%

DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints

Liming Han, Yimin Lin, Guoguang Du, Shiguo Lian

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by IROS 2019, demo video: https://www.youtube.com/watch?v=fMeqCcpBCdM&feature=youtu.be

1905.07290 2019-05-20 cs.CV cs.LG cs.RO eess.IV 62%

LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving

Ahmad El Sallab, Ibrahim Sobh, Mohamed Zahran, Nader Essam

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted at ICML Workshop on AI for Autonomous Driving

1905.00160 2019-05-08 cs.CV cs.RO 62%

Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perception

Braden Hurl, Krzysztof Czarnecki, Steven Waslander

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1904.12433 2019-04-30 cs.CV cs.RO 62%

Automatic extrinsic calibration between a camera and a 3D Lidar using 3D point and plane correspondences

Surabhi Verma, Julie Stephany Berrio, Stewart Worrall, Eduardo Nebot

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1904.04281 2019-04-10 cs.CV cs.AI cs.LG cs.RO 62%

3D Local Features for Direct Pairwise Registration

Haowen Deng, Tolga Birdal, Slobodan Ilic

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments To appear in CVPR 2019. 16 pages, identical to the camera ready submission

1903.09169 2019-03-25 cs.CV cs.RO 62%

Quantitative Depth Quality Assessment of RGBD Cameras At Close Range Using 3D Printed Fixtures

Michele Pratusevich, Jason Chrisos, Shreyas Aditya

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 4 pages; submitted to ICRA 2019 HAMM Workshop

1903.05889 2019-03-15 cs.RO cs.CV 62%

Detection and Tracking of Small Objects in Sparse 3D Laser Range Data

Jan Razlaw, Jan Quenzel, Sven Behnke

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, to appear May 2019

1706.02908 2019-03-14 cs.RO cs.CV 62%

Multi-Modal Obstacle Detection in Unstructured Environments with Conditional Random Fields

Mikkel Kragh, James Underwood

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments This is the accepted version of the following article: Kragh M, Underwood J. Multimodal obstacle detection in unstructured environments with conditional random fields. J Field Robotics. 2019, 1-20., which has been published in final form at https://doi.org/10.1002/rob.21866

1903.03911 2019-03-13 cs.CV cs.GR 62%

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

Xiaogang Wang, Bin Zhou, Yahao Shi, Xiaowu Chen, Qinping Zhao, Kai Xu

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Comments CVPR 2019 (oral presentation); Corresponding author: Kai Xu (kevin.kai.xu@gmail.com); Project page: www.kevinkaixu.net/projects/shape2motion.html

1903.01568 2019-03-07 cs.CV cs.RO 62%

The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes

Abhishek Patil, Srikanth Malla, Haiming Gang, Yi-Ting Chen

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments The dataset is available at https://usa.honda-ri.com/H3D

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2019

1809.05825 2019-03-05 cs.CV cs.RO 62%

Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data

Michael Danielczuk, Matthew Matl, Saurabh Gupta, Andrew Li, Andrew Lee, Jeffrey Mahler, Ken Goldberg

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments In proceedings of ICRA 2019/

1807.04870 2019-02-05 cs.CV cs.RO 62%

Extracting Contact and Motion from Manipulation Videos

Konstantinos Zampogiannis, Kanishka Ganguly, Cornelia Fermuller, Yiannis Aloimonos

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1810.09631 2018-10-24 cs.CV cs.RO 62%

Point-cloud-based place recognition using CNN feature extraction

Ting Sun, Ming Liu, Haoyang Ye, Dit-Yan Yeung

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1809.07417 2018-09-21 cs.CV cs.GR 62%

Deep Part Induction from Articulated Object Pairs

Li Yi, Haibin Huang, Difan Liu, Evangelos Kalogerakis, Hao Su, Leonidas Guibas

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

1804.05132 2018-09-10 cs.RO cs.CV 62%

Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection

Di Feng, Lars Rosenbaum, Klaus Dietmayer

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to present in the 21st IEEE International Conference on Intelligent Transportation Systems (ITSC 2018)

1808.10322 2018-08-31 cs.CV cs.CG cs.LG cs.RO 62%

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

Haowen Deng, Tolga Birdal, Slobodan Ilic

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted for publication at ECCV 2018

1807.10517 2018-07-30 cs.CV cs.GR 62%

FARM: Functional Automatic Registration Method for 3D Human Bodies

Riccardo Marin, Simone Melzi, Emanuele Rodolà, Umberto Castellani

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.GR

Comments Under submission to CGF

1804.05178 2018-04-17 cs.CV cs.RO 62%

LiDAR and Camera Calibration using Motion Estimated by Sensor Fusion Odometry

Ryoichi Ishikawa, Takeshi Oishi, Katsushi Ikeuchi

专题命中点云：point cloud(abstract)；分类 cs.CV、cs.RO

1. 点云 7719 篇

PCN: Point Completion Network

3D Ken Burns Effect from a Single Image

MLOD: A multi-view 3D object detection based on robust feature fusion method

Deep Workpiece Region Segmentation for Bin Picking

6-DOF GraspNet: Variational Grasp Generation for Object Manipulation

SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences

Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks

RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving

Lidar-based Object Classification with Explicit Occlusion Modeling

Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints

LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving

Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perception

Automatic extrinsic calibration between a camera and a 3D Lidar using 3D point and plane correspondences

3D Local Features for Direct Pairwise Registration

Quantitative Depth Quality Assessment of RGBD Cameras At Close Range Using 3D Printed Fixtures

Detection and Tracking of Small Objects in Sparse 3D Laser Range Data

Multi-Modal Obstacle Detection in Unstructured Environments with Conditional Random Fields

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes

Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data

Extracting Contact and Motion from Manipulation Videos

Point-cloud-based place recognition using CNN feature extraction

Deep Part Induction from Articulated Object Pairs

Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

FARM: Functional Automatic Registration Method for 3D Human Bodies

LiDAR and Camera Calibration using Motion Estimated by Sensor Fusion Odometry