3D 视觉 - arXivDaily 专题

1912.13077 2022-05-19 cs.CV cs.LG cs.RO 62%

Learning Selective Sensor Fusion for States Estimation

Changhao Chen, Stefano Rosa, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham

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

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS). arXiv admin note: text overlap with arXiv:1903.01534

2205.08150 2022-05-18 cs.CV cs.RO 62%

UnPWC-SVDLO: Multi-SVD on PointPWC for Unsupervised Lidar Odometry

Yiming Tu

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

2205.07096 2022-05-17 cs.CV cs.RO 62%

Multi-modal curb detection and filtering

Sandipan Das, Navid Mahabadi, Saikat Chatterjee, Maurice Fallon

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

2205.04028 2022-05-10 cs.RO cs.CV 62%

Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions

Chilam Cheang, Haitao Lin, Yanwei Fu, Xiangyang Xue

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

Comments accepted by ICRA2022

2205.03654 2022-05-10 cs.RO cs.CV 62%

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

Prajval Kumar Murali, Cong Wang, Ravinder Dahiya, Mohsen Kaboli

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

2105.01765 2022-05-05 cs.CV cs.RO 62%

Enabling 3D Object Detection with a Low-Resolution LiDAR

Lin Bai, Yiming Zhao, Xinming Huang

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

2105.00373 2022-05-05 cs.RO cs.AI cs.CV cs.LG 62%

Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving

Hanjiang Hu, Zuxin Liu, Sharad Chitlangia, Akhil Agnihotri, Ding Zhao

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

Comments CVPR 2022 camera-ready version:15 pages, 14 figures, 9 tables

2205.01460 2022-05-04 cs.CV cs.RO 62%

3D Semantic Scene Perception using Distributed Smart Edge Sensors

Simon Bultmann, Sven Behnke

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

Comments 17th International Conference on Intelligent Autonomous Systems (IAS), Zagreb, Croatia, June 2022

2204.13590 2022-04-29 cs.CV cs.AI cs.LG cs.RO 62%

Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms

Nachuan Ma, Jiahe Fan, Wenshuo Wang, Jin Wu, Yu Jiang, Lihua Xie, Rui Fan

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

Comments accepted to Transportation Safety and Environment

2104.11467 2022-04-26 eess.SP cs.CV cs.LG cs.RO 62%

Probabilistic Rainfall Estimation from Automotive Lidar

Robin Karlsson, David Robert Wong, Kazunari Kawabata, Simon Thompson, Naoki Sakai

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

Comments Accepted for IEEE IV 2022

2107.06165 2022-04-21 cs.CV cs.GR 62%

3D Parametric Wireframe Extraction Based on Distance Fields

Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev

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

2203.16268 2022-03-31 cs.CV cs.RO 62%

Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking

Guangming Wang, Chensheng Peng, Jinpeng Zhang, Hesheng Wang

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

Comments 9 pages, 5 figures, under review

2106.07545 2022-03-25 cs.CV cs.RO 62%

PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars

Qi Chen, Sourabh Vora, Oscar Beijbom

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

Comments NeurIPS 2021; code and pretrained models available at https://github.com/motional/polarstream

2203.09510 2022-03-18 cs.CV cs.AI cs.LG cs.RO 62%

DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection

Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan

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

Comments https://github.com/Divadi/DetMatch

2203.06612 2022-03-15 cs.CV cs.RO 62%

A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments

Hyungtae Lim, Suyong Yeon, Soohyun Ryu, Yonghan Lee, Youngji Kim, Jaeseong Yun, Euigon Jung, Donghwan Lee, Hyun Myung

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

Comments 8 pages. Acccepted by ICRA 2022

2108.05560 2022-03-11 cs.RO cs.CV 62%

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

Hyungtae Lim, Minho Oh, Hyun Myung

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

2203.04064 2022-03-09 cs.RO cs.CV 62%

Analyzing General-Purpose Deep-Learning Detection and Segmentation Models with Images from a Lidar as a Camera Sensor

Yu Xianjia, Sahar Salimpour, Jorge Peña Queralta, Tomi Westerlund

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

2203.01152 2022-03-03 cs.CV cs.GR 62%

DisARM: Displacement Aware Relation Module for 3D Detection

Yao Duan, Chenyang Zhu, Yuqing Lan, Renjiao Yi, Xinwang Liu, Kai Xu

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

2111.14693 2022-03-03 cs.RO cs.AI cs.CV cs.LG 62%

SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning

Jun Lv, Qiaojun Yu, Lin Shao, Wenhai Liu, Wenqiang Xu, Cewu Lu

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

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2022

2203.00080 2022-03-02 cs.CV cs.LG cs.RO 62%

Deep Camera Pose Regression Using Pseudo-LiDAR

Ali Raza, Lazar Lolic, Shahmir Akhter, Alfonso Dela Cruz, Michael Liut

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

Comments 7 pages, 5 figures, 2 tables

2111.00440 2022-03-01 cs.CV cs.RO 62%

Loop closure detection using local 3D deep descriptors

Youjie Zhou, Yiming Wang, Fabio Poiesi, Qi Qin, Yi Wan

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

Comments This work is accepted for publication in IEEE Robotics and Automation Letters

2010.09343 2022-02-10 cs.CV cs.RO 62%

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks

Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li

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

Comments Accepted to CoRL 2020

2105.14829 2022-02-07 cs.RO cs.AI cs.CV cs.LG 62%

Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

Stephen James, Andrew J. Davison

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

Comments IEEE Robotics and Automation Letters, 2022 (+ presentation at ICRA 2022). Videos and code found at: https://sites.google.com/view/q-attention

2107.00346 2022-01-21 cs.CV cs.RO 62%

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

Kunyu Peng, Juncong Fei, Kailun Yang, Alina Roitberg, Jiaming Zhang, Frank Bieder, Philipp Heidenreich, Christoph Stiller, Rainer Stiefelhagen

专题命中点云：3D vision(abstract)；分类 cs.CV、cs.RO

Comments Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS). Code is publicly available at https://github.com/KPeng9510/MASS

2201.05972 2022-01-19 cs.CV cs.AI cs.RO 62%

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

Shuangjie Xu, Rui Wan, Maosheng Ye, Xiaoyi Zou, Tongyi Cao

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

Comments Accepted by the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)

2003.06233 2022-01-14 cs.GR cs.CV 62%

Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation

Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu

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

Comments CVPR 2020

2201.00596 2022-01-04 cs.RO cs.CV 62%

LiDAR Point--to--point Correspondences for Rigorous Registration of Kinematic Scanning in Dynamic Networks

Aurélien Brun, Davide Antonio Cucci, Jan Skaloud

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

2112.06539 2021-12-28 cs.RO cs.CV 62%

MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity

Kamil Żywanowski, Adam Banaszczyk, Michał R. Nowicki, Jacek Komorowski

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

2109.03805 2021-12-28 cs.CV cs.AI cs.LG cs.RO 62%

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

Whye Kit Fong, Rohit Mohan, Juana Valeria Hurtado, Lubing Zhou, Holger Caesar, Oscar Beijbom, Abhinav Valada

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

Comments The benchmark is available at https://www.nuscenes.org

2112.12610 2021-12-24 cs.CV cs.RO 62%

PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving

Pengchuan Xiao, Zhenlei Shao, Steven Hao, Zishuo Zhang, Xiaolin Chai, Judy Jiao, Zesong Li, Jian Wu, Kai Sun, Kun Jiang, Yunlong Wang, Diange Yang

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

Comments This paper has been published on ITSC'2021, please check the website of the PandaSet for more information: https://pandaset.org/

1. 点云 7719 篇

Learning Selective Sensor Fusion for States Estimation

UnPWC-SVDLO: Multi-SVD on PointPWC for Unsupervised Lidar Odometry

Multi-modal curb detection and filtering

Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

Enabling 3D Object Detection with a Low-Resolution LiDAR

Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving

3D Semantic Scene Perception using Distributed Smart Edge Sensors

Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms

Probabilistic Rainfall Estimation from Automotive Lidar

3D Parametric Wireframe Extraction Based on Distance Fields

Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking

PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars

DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection

A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments

Patchwork: Concentric Zone-based Region-wise Ground Segmentation with Ground Likelihood Estimation Using a 3D LiDAR Sensor

Analyzing General-Purpose Deep-Learning Detection and Segmentation Models with Images from a Lidar as a Camera Sensor

DisARM: Displacement Aware Relation Module for 3D Detection

SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning

Deep Camera Pose Regression Using Pseudo-LiDAR

Loop closure detection using local 3D deep descriptors

SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks

Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation

LiDAR Point--to--point Correspondences for Rigorous Registration of Kinematic Scanning in Dynamic Networks

MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving