3D 视觉 - arXivDaily 专题

2209.09777 2022-10-05 cs.RO 57%

WGICP: Differentiable Weighted GICP-Based Lidar Odometry

Sanghyun Son, Jing Liang, Ming Lin, Dinesh Manocha

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 6 pages

2207.11709 2022-10-04 cs.CV 57%

TVCalib: Camera Calibration for Sports Field Registration in Soccer

Jonas Theiner, Ralph Ewerth

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted for publication at WACV'23

2205.12519 2022-10-04 cs.CV 57%

Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

Sushruth Nagesh, Asfiya Baig, Savitha Srinivasan, Akshay Rangesh, Mohan Trivedi

专题命中点云：point cloud(abstract)；分类 cs.CV

2209.15252 2022-10-03 cs.CV eess.IV 57%

PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detection

Konrad Lis, Tomasz Kryjak

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted for the ICCVG 2022 conference

2209.14690 2022-09-30 cs.CV 57%

Prompt-guided Scene Generation for 3D Zero-Shot Learning

Majid Nasiri, Ali Cheraghian, Townim Faisal Chowdhury, Sahar Ahmadi, Morteza Saberi, Shafin Rahman

专题命中点云：point cloud(abstract)；分类 cs.CV

2209.14284 2022-09-29 cs.CV 57%

DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations

Zoey Qiuyu Chen, Karl Van Wyk, Yu-Wei Chao, Wei Yang, Arsalan Mousavian, Abhishek Gupta, Dieter Fox

专题命中点云：point cloud(abstract)；分类 cs.CV

2209.13130 2022-09-28 cs.CV cs.AI 57%

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

Chaokang Jiang, Guangming Wang, Yanzi Miao, Hesheng Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 9 pages, 5 figures; This paper has been accepted by IEEE Transactions on Industrial Informatics

2206.12628 2022-09-28 cs.RO 57%

FreSCo: Frequency-Domain Scan Context for LiDAR-based Place Recognition with Translation and Rotation Invariance

Yongzhi Fan, Xin Du, Lun Luo, Jizhong Shen

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 8 pages, 10 figures. Accepted for ICARCV 2022

2202.00868 2022-09-28 cs.RO 57%

VIRDO: Visio-tactile Implicit Representations of Deformable Objects

Youngsun Wi, Pete Florence, Andy Zeng, Nima Fazeli

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments This work has been accepted to ICRA 2022

2011.14497 2022-09-27 cs.RO 57%

Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling

Kavisha Vidanapathirana, Peyman Moghadam, Ben Harwood, Muming Zhao, Sridha Sridharan, Clinton Fookes

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments ICRA 2021. Implementation available at: https://github.com/csiro-robotics/locus

2011.09128 2022-09-27 cs.CV cs.LG cs.NE 57%

MGIC: Multigrid-in-Channels Neural Network Architectures

Moshe Eliasof, Jonathan Ephrath, Lars Ruthotto, Eran Treister

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments This paper supersedes arXiv:2006.06799 Accepted to SISC

2209.12254 2022-09-27 cs.CV 57%

From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion

Rui Wan, Shuangjie Xu, Wei Wu, Xiaoyi Zou, Tongyi Cao

专题命中点云：point cloud(abstract)；分类 cs.CV

2209.11488 2022-09-26 cs.CV 57%

GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition

Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Jun He

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages

2209.10733 2022-09-23 cs.CV 57%

FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection

Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages, 3 figures

2205.13764 2022-09-21 cs.CV 57%

Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images

Zhi Tian, Xiangxiang Chu, Xiaoming Wang, Xiaolin Wei, Chunhua Shen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to: Proc. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022. 14 pages

2209.08539 2022-09-20 cs.RO 57%

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

Zhuozhu Jian, Zihong Yan, Xuanang Lei, Zihong Lu, Bin Lan, Xueqian Wang, Bin Liang

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Submitted to IEEE International Conference on Robotics and Automation (ICRA) 2023

2209.08132 2022-09-20 cs.CV 57%

Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental Model

Ananya Jana, Hrebesh Molly Subhash, Dimitris Metaxas

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments accepted to SIPAIM 2022

2209.07419 2022-09-16 cs.CV 57%

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Chaokang Jiang, Guangming Wang, Jinxing Wu, Yanzi Miao, Hesheng Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages, 4 figures; under review

2209.07069 2022-09-16 cs.CV 57%

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

Gengxin Liu, Oliver van Kaick, Hui Huang, Ruizhen Hu

专题命中点云：point cloud(abstract)；分类 cs.CV

Journal ref Computational Visual Media 2022

2111.02135 2022-09-16 cs.CV 57%

Efficient 3D Deep LiDAR Odometry

Guangming Wang, Xinrui Wu, Shuyang Jiang, Zhe Liu, Hesheng Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 17 pages, 13 figures. Accepted by PAMI 2022. arXiv admin note: substantial text overlap with arXiv:2012.00972

2209.06383 2022-09-15 cs.CV 57%

Analysis of Quantization on MLP-based Vision Models

Lingran Zhao, Zhen Dong, Kurt Keutzer

专题命中点云：point cloud(abstract)；分类 cs.CV

2209.05588 2022-09-14 cs.CV 57%

CenterFormer: Center-based Transformer for 3D Object Detection

Zixiang Zhou, Xiangchen Zhao, Yu Wang, Panqu Wang, Hassan Foroosh

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to ECCV 2022 (oral)

2209.04945 2022-09-13 cs.CV 57%

Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

Guangming Wang, Zhiheng Feng, Chaokang Jiang, Hesheng Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 12 pages, 9 figures, under review

2209.03226 2022-09-08 cs.RO 57%

On the Importance of Quantifying Visibility for Autonomous Vehicles under Extreme Precipitation

Clément Courcelle, Dominic Baril, François Pomerleau, Johann Laconte

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Submitted to Intelligent Vehicles and Transportation Volume 3 - De Gruyter

2208.05383 2022-09-07 cs.RO cs.SY eess.SY 57%

Precise Repositioning of Robotic Ultrasound: Improving Registration-based Motion Compensation using Ultrasound Confidence Optimization

Zhongliang Jiang, Nehil Danis, Yuan Bi, Mingchuan Zhou, Markus Kroenke, Thomas Wendler, Nassir Navab

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments The paper has been accepted by IEEE TIM. Video: https://www.youtube.com/watch?v=MUtgSXS7EZI

2209.00860 2022-09-05 cs.CV 57%

Real-time 3D Single Object Tracking with Transformer

Jiayao Shan, Sifan Zhou, Yubo Cui, Zheng Fang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments IEEE Transactions on Multimedia. arXiv admin note: text overlap with arXiv:2108.06455

2207.12654 2022-09-05 cs.CV 57%

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

Junbo Yin, Dingfu Zhou, Liangjun Zhang, Jin Fang, Cheng-Zhong Xu, Jianbing Shen, Wenguan Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to ECCV 2022. Code: https://github.com/yinjunbo/ProposalContrast

2205.05979 2022-09-05 cs.CV 57%

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

Xuesong Chen, Shaoshuai Shi, Benjin Zhu, Ka Chun Cheung, Hang Xu, Hongsheng Li

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ECCV 2022

2208.14848 2022-09-01 cs.RO 57%

PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM

Yifan Duan, Jie Peng, Yu Zhang, Jianmin Ji, Yanyong Zhang

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 7 pages, 5 figures. Accepted for IEEE IROS 2022

2208.14796 2022-09-01 cs.CV 57%

3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning

Baian Chen, Liangliang Nan, Haoran Xie, Dening Lu, Fu Lee Wang, Mingqiang Wei

专题命中点云：point cloud(abstract)；分类 cs.CV

1. 点云 7723 篇

WGICP: Differentiable Weighted GICP-Based Lidar Odometry

TVCalib: Camera Calibration for Sports Field Registration in Soccer

Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

PointPillars Backbone Type Selection For Fast and Accurate LiDAR Object Detection

Prompt-guided Scene Generation for 3D Zero-Shot Learning

DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

FreSCo: Frequency-Domain Scan Context for LiDAR-based Place Recognition with Translation and Rotation Invariance

VIRDO: Visio-tactile Implicit Representations of Deformable Objects

Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling

MGIC: Multigrid-in-Channels Neural Network Architectures

From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion

GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition

FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection

Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental Model

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

Efficient 3D Deep LiDAR Odometry

Analysis of Quantization on MLP-based Vision Models

CenterFormer: Center-based Transformer for 3D Object Detection

Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

On the Importance of Quantifying Visibility for Autonomous Vehicles under Extreme Precipitation

Precise Repositioning of Robotic Ultrasound: Improving Registration-based Motion Compensation using Ultrasound Confidence Optimization

Real-time 3D Single Object Tracking with Transformer

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

PFilter: Building Persistent Maps through Feature Filtering for Fast and Accurate LiDAR-based SLAM

3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning