3D 视觉 - arXivDaily 专题

2105.09843 2021-05-21 cs.RO 57%

Teat Pose Estimation via RGBD Segmentation for Automated Milking

Nicolas Borla, Fabian Kuster, Jonas Langenegger, Juan Ribera, Marcel Honegger, Giovanni Toffetti

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Accepted for publication at the "Task-Informed Grasping: Agri-Food manipulation" (TIG-III) Workshop at ICRA 2021

2105.08502 2021-05-19 cs.RO 57%

GPR: Grasp Pose Refinement Network for Cluttered Scenes

Wei Wei, Yongkang Luo, Fuyu Li, Guangyun Xu, Jun Zhong, Wanyi Li, Peng Wang

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 7 pages, accepted to ICRA2021

2105.08177 2021-05-19 cs.SD cs.GR eess.AS 57%

Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding

Hsien-Yu Meng, Zhenyu Tang, Dinesh Manocha

专题命中点云：point cloud(abstract)；分类 cs.GR

Comments IJCAI 2021 main track paper

2105.07647 2021-05-18 cs.CV 57%

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

Yi Wei, Shang Su, Jiwen Lu, Jie Zhou

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to ICRA 2021

1910.06849 2021-05-18 cs.CV cs.LG eess.IV 57%

DeepGCNs: Making GCNs Go as Deep as CNNs

Guohao Li, Matthias Müller, Guocheng Qian, Itzel C. Delgadillo, Abdulellah Abualshour, Ali Thabet, Bernard Ghanem

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at TPAMI. This work is a journal extension of our ICCV'19 paper arXiv:1904.03751. The first three authors contributed equally

1905.10725 2021-05-17 stat.ML cs.CV cs.LG math.DG 57%

Efficient Weingarten Map and Curvature Estimation on Manifolds

Yueqi Cao, Didong Li, Huafei Sun, Amir H Assadi, Shiqiang Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 23 pages, 8 figures

Journal ref Machine Learning (2021)

2105.06461 2021-05-14 cs.CV cs.AI cs.LG cs.MM 57%

3D Spatial Recognition without Spatially Labeled 3D

Zhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit Girdhar

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments CVPR 2021

2012.06628 2021-05-11 cs.CV 57%

Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image

Zuoyue Li, Zhenqiang Li, Zhaopeng Cui, Rongjun Qin, Marc Pollefeys, Martin R. Oswald

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Technical Report

2105.02714 2021-05-07 cs.CV cs.AI 57%

Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration

Dvir Ginzburg, Dan Raviv

专题命中点云：point cloud(abstract)；分类 cs.CV

1906.11555 2021-05-07 cs.CV 57%

Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov

专题命中点云：point cloud(abstract)；分类 cs.CV

2105.01793 2021-05-06 cs.CV eess.IV 57%

Intensity Harmonization for Airborne LiDAR

David Jones, Nathan Jacobs

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments IGARSS 2021. Project website with video and code at https://davidthomasjones.me/publications/airborne-lidar-intensity-harmonization

2103.12241 2021-05-04 cs.RO 57%

Multimodal Data Fusion for Power-On-and-Go Robotic Systems in Retail

Shubham Sonawani, Kailas Maneparambil, Heni Ben Amor

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments POGO Workshop, RSS 2020

2011.00800 2021-05-03 cs.RO 57%

Real-to-Sim Registration of Deformable Soft Tissue with Position-Based Dynamics for Surgical Robot Autonomy

Fei Liu, Zihan Li, Yunhai Han, Jingpei Lu, Florian Richter, Michael C. Yip

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Fei Liu and Zihan Li contributed equally to this work. Final version of this paper is going to be published in ICRA 2021

2010.14476 2021-04-29 cs.AI cs.CV 57%

Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaa)

Mladen Popović, Maruf A. Dhali, Lambert Schomaker

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 23 pages, 15 pages of supplementary materials, submitted to PLOS ONE on 19 October 2019

Journal ref PLoS ONE 2021

2011.03209 2021-04-28 cs.CG cs.GR cs.HC 57%

Mapper Interactive: A Scalable, Extendable, and Interactive Toolbox for the Visual Exploration of High-Dimensional Data

Youjia Zhou, Nithin Chalapathi, Archit Rathore, Yaodong Zhao, Bei Wang

专题命中点云：point cloud(abstract)；分类 cs.GR

2012.13901 2021-04-27 cs.CV 57%

LCCNet: LiDAR and Camera Self-Calibration using Cost Volume Network

Xudong Lv, Boya Wang, Dong Ye, Shuo Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

2104.11785 2021-04-27 cs.NI cs.CV 57%

On the Role of Sensor Fusion for Object Detection in Future Vehicular Networks

Valentina Rossi, Paolo Testolina, Marco Giordani, Michele Zorzi

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments This paper has been accepted for presentation at the Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit). 6 pages, 6 figures, 1 table

2104.00678 2021-04-26 cs.CV 57%

Group-Free 3D Object Detection via Transformers

Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong

专题命中点云：point cloud(abstract)；分类 cs.CV

2012.12741 2021-04-22 cs.CV cs.AI 57%

Exploring Data Augmentation for Multi-Modality 3D Object Detection

Wenwei Zhang, Zhe Wang, Chen Change Loy

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Technical Report

2011.12953 2021-04-20 cs.CV 57%

Unsupervised Object Detection with LiDAR Clues

Hao Tian, Yuntao Chen, Jifeng Dai, Zhaoxiang Zhang, Xizhou Zhu

专题命中点云：point cloud(abstract)；分类 cs.CV

2104.08683 2021-04-20 cs.CV 57%

Self-Supervised Pillar Motion Learning for Autonomous Driving

Chenxu Luo, Xiaodong Yang, Alan Yuille

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments cvpr2021

2104.05327 2021-04-15 cs.CV 57%

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

Jacek Komorowski, Monika Wysoczanska, Tomasz Trzcinski

专题命中点云：point cloud(abstract)；分类 cs.CV

2103.07679 2021-04-15 cs.CL cs.CV 57%

OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding

Ke-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su, Jen-Wei Wang, Yu-Siang Wang, Winston H. Hsu, Wen-Chin Chen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments NAACL 2021

2104.06041 2021-04-14 cs.CV 57%

OCM3D: Object-Centric Monocular 3D Object Detection

Liang Peng, Fei Liu, Senbo Yan, Xiaofei He, Deng Cai

专题命中点云：point cloud(abstract)；分类 cs.CV

2004.01803 2021-04-14 cs.CV 57%

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

Chenfeng Xu, Bichen Wu, Zining Wang, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ECCV 2020. Code and data are available at: https://github.com/chenfengxu714/SqueezeSegV3.git

2011.09141 2021-04-14 cs.CV cs.LG 57%

Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data

Christoph B. Rist, David Emmerichs, Markus Enzweiler, Dariu M. Gavrila

专题命中点云：point cloud(abstract)；分类 cs.CV

2104.05328 2021-04-13 cs.CV 57%

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

Sk Aziz Ali, Kerem Kahraman, Gerd Reis, Didier Stricker

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Computer Vision and Pattern Recognition (CVPR) 2021, (*Accepted)

1912.13192 2021-04-12 cs.CV cs.LG eess.IV 57%

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by CVPR 2020. arXiv admin note: substantial text overlap with arXiv:2102.00463

2104.03851 2021-04-09 cs.CV 57%

CoCoNets: Continuous Contrastive 3D Scene Representations

Shamit Lal, Mihir Prabhudesai, Ishita Mediratta, Adam W. Harley, Katerina Fragkiadaki

专题命中点云：point cloud(abstract)；分类 cs.CV

2104.00706 2021-04-09 cs.LG cs.CV 57%

BRepNet: A topological message passing system for solid models

Joseph G. Lambourne, Karl D. D. Willis, Pradeep Kumar Jayaraman, Aditya Sanghi, Peter Meltzer, Hooman Shayani

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments CVPR 2021 Oral

1. 点云 7730 篇

Teat Pose Estimation via RGBD Segmentation for Automated Milking

GPR: Grasp Pose Refinement Network for Cluttered Scenes

Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

DeepGCNs: Making GCNs Go as Deep as CNNs

Efficient Weingarten Map and Curvature Estimation on Manifolds

3D Spatial Recognition without Spatially Labeled 3D

Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image

Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration

Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

Intensity Harmonization for Airborne LiDAR

Multimodal Data Fusion for Power-On-and-Go Robotic Systems in Retail

Real-to-Sim Registration of Deformable Soft Tissue with Position-Based Dynamics for Surgical Robot Autonomy

Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaa)

Mapper Interactive: A Scalable, Extendable, and Interactive Toolbox for the Visual Exploration of High-Dimensional Data

LCCNet: LiDAR and Camera Self-Calibration using Cost Volume Network

On the Role of Sensor Fusion for Object Detection in Future Vehicular Networks

Group-Free 3D Object Detection via Transformers

Exploring Data Augmentation for Multi-Modality 3D Object Detection

Unsupervised Object Detection with LiDAR Clues

Self-Supervised Pillar Motion Learning for Autonomous Driving

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding

OCM3D: Object-Centric Monocular 3D Object Detection

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

CoCoNets: Continuous Contrastive 3D Scene Representations

BRepNet: A topological message passing system for solid models