3D 视觉 - arXivDaily 专题

2104.14118 2021-12-10 cs.RO cs.CV 62%

REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter

Hanbo Zhang, Deyu Yang, Han Wang, Binglei Zhao, Xuguang Lan, Jishiyu Ding, Nanning Zheng

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

2112.02205 2021-12-07 cs.CV cs.AI cs.LG cs.RO 62%

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Qiangeng Xu, Yiqi Zhong, Ulrich Neumann

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

Journal ref AAAI2022

2112.00169 2021-12-07 cs.CV cs.GR 62%

3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image

Fangzhou Mu, Jian Wang, Yicheng Wu, Yin Li

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

Comments Project page: http://pages.cs.wisc.edu/~fmu/style3d/

2112.00958 2021-12-03 cs.CV cs.GR cs.LG 62%

Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting

Sourav Biswas, Kangxue Yin, Maria Shugrina, Sanja Fidler, Sameh Khamis

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

2111.13838 2021-11-30 cs.CV cs.RO 62%

DSC: Deep Scan Context Descriptor for Large-Scale Place Recognition

Jiafeng Cui, Tengfei Huang, Yingfeng Cai, Junqiao Zhao, Lu Xiong, Zhuoping Yu

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

2111.11481 2021-11-25 cs.CV cs.RO 62%

Real-time ground filtering algorithm of cloud points acquired using Terrestrial Laser Scanner (TLS)

Nelson Diaz, Omar Gallo, Jhon Caceres, Hernan Porras

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

Comments 25 pages, 7 figures

2111.11739 2021-11-24 cs.CV cs.RO 62%

AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition

Haowen Lai, Peng Yin, Sebastian Scherer

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

Comments 8 pages, 7 figures

2111.11615 2021-11-24 cs.CV cs.RO 62%

PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network

Faris Azhari, Charlotte Sennersten, Michael Milford, Thierry Peynot

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

Comments submitted, to be published

2109.08817 2021-11-18 cs.RO cs.AI cs.CV cs.LG 62%

Learning to Regrasp by Learning to Place

Shuo Cheng, Kaichun Mo, Lin Shao

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

Comments Accepted to Conference on Robot Learning (CoRL) 2021

2111.06881 2021-11-15 cs.CV cs.LG cs.RO 62%

Multimodal Virtual Point 3D Detection

Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl

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

Comments NeurIPS 2021, code available at https://tianweiy.github.io/mvp/

2107.03438 2021-11-08 cs.RO cs.CL cs.CV 62%

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

Junha Roh, Karthik Desingh, Ali Farhadi, Dieter Fox

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

Comments 11 pages, 3 figures

2102.08009 2021-11-05 cs.CV cs.LG cs.RO 62%

EfficientLPS: Efficient LiDAR Panoptic Segmentation

Kshitij Sirohi, Rohit Mohan, Daniel Büscher, Wolfram Burgard, Abhinav Valada

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

Comments Ranked #1 on SemanticKITTI and nuScenes panoptic segmentation benchmarks

Journal ref IEEE Transactions on Robotics (T-RO), 2021

2110.15179 2021-10-29 cs.CV cs.RO 62%

A Comparative Study of Coarse to Dense 3D Indoor Scene Registration Algorithms

Abdenour Amamra, Khalid Boumaza

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

Comments Accepted in International Conference on Advanced Electrical Engineering (ICAEE)

Journal ref In 2019 International Conference on Advanced Electrical Engineering (ICAEE) (pp. 1-6). IEEE (2019)

2110.10189 2021-10-22 cs.RO cs.AI cs.CL cs.CV cs.LG 62%

StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects

Weiyu Liu, Chris Paxton, Tucker Hermans, Dieter Fox

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

2110.09355 2021-10-19 cs.CV cs.RO 62%

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger, Horst Bischof

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

Comments Accepted to BMVC 2021

2001.04286 2021-10-19 math.OC cs.CV cs.LG cs.RO 62%

Nonparametric Continuous Sensor Registration

William Clark, Maani Ghaffari, Anthony Bloch

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

Comments 50 pages. Accepted for Journal of Machine Learning Research. arXiv admin note: text overlap with arXiv:1904.02266

2110.07911 2021-10-18 cs.CV cs.RO 62%

Learning to Infer Kinematic Hierarchies for Novel Object Instances

Hameed Abdul-Rashid, Miles Freeman, Ben Abbatematteo, George Konidaris, Daniel Ritchie

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

2110.06923 2021-10-14 cs.CV cs.AI cs.LG cs.RO 62%

Object DGCNN: 3D Object Detection using Dynamic Graphs

Yue Wang, Justin Solomon

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

Comments Accepted to NeurIPS 2021

2109.02711 2021-10-13 cs.CV cs.AI cs.LG cs.RO 62%

Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms

Rui Fan, Hengli Wang, Yuan Wang, Ming Liu, Ioannis Pitas

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

Comments accepted as a regular paper to IEEE Transactions on Image Processing

2110.04955 2021-10-12 cs.CV cs.GR 62%

BuildingNet: Learning to Label 3D Buildings

Pratheba Selvaraju, Mohamed Nabail, Marios Loizou, Maria Maslioukova, Melinos Averkiou, Andreas Andreou, Siddhartha Chaudhuri, Evangelos Kalogerakis

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

Comments Accepted to ICCV 2021 (oral)

2012.13755 2021-10-12 cs.CV cs.RO 62%

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

Hsu-kuang Chiu, Jie Li, Rares Ambrus, Jeannette Bohg

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

Comments IEEE International Conference on Robotics and Automation (ICRA) 2021

2109.11644 2021-09-27 cs.RO cs.AI cs.CV cs.LG 62%

A Learned Stereo Depth System for Robotic Manipulation in Homes

Krishna Shankar, Mark Tjersland, Jeremy Ma, Kevin Stone, Max Bajracharya

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

2103.09448 2021-09-23 cs.CV cs.CR cs.GR cs.LG 62%

Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection

Mazen Abdelfattah, Kaiwen Yuan, Z. Jane Wang, Rabab Ward

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

Comments arXiv admin note: text overlap with arXiv:2101.10747 Updates in v2: Expanded conclusion and future work, reduced Figure 5's size, and a small correction in Table 3

2103.08764 2021-09-16 cs.CV cs.RO 62%

Fast and Accurate: Video Enhancement using Sparse Depth

Yu Feng, Patrick Hansen, Paul N. Whatmough, Guoyu Lu, Yuhao Zhu

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

2109.01533 2021-09-06 cs.CV cs.RO 62%

UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry

Yiming Tu, Jin Xie

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

Comments 14 pages, accepted by ACPR2021

2108.00552 2021-08-31 cs.CV cs.RO 62%

PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embedding

Peng Yin, Lingyun Xu, Ziyue Feng, Anton Egorov, Bing Li

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

Comments 12 pages, 12 figures, accepted by IEEE Transactions on Intelligent Transportation Systems

2108.10608 2021-08-25 cs.CV cs.LG cs.RO 62%

Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery

Xue Hu, Anh Nguyen, Ferdinando Rodriguez y Baena

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

Comments This work has been submitted to the IEEE for possible publication

2108.06608 2021-08-17 cs.CV cs.RO 62%

Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles

Simon Bultmann, Jan Quenzel, Sven Behnke

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

Comments Accepted for: 10th European Conference on Mobile Robots (ECMR), Bonn, Germany, September 2021

2108.01495 2021-08-04 cs.RO cs.CV 62%

Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study

Timm Linder, Narunas Vaskevicius, Robert Schirmer, Kai O. Arras

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

Comments Accepted for publication at 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2012.03321 2021-07-29 cs.RO cs.CV 62%

Global Unifying Intrinsic Calibration for Spinning and Solid-State LiDARs

Jiunn-Kai Huang, Chenxi Feng, Madhav Achar, Maani Ghaffari, Jessy W. Grizzle

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

1. 点云 7719 篇

REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image

Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting

DSC: Deep Scan Context Descriptor for Large-Scale Place Recognition

Real-time ground filtering algorithm of cloud points acquired using Terrestrial Laser Scanner (TLS)

AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition

PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network

Learning to Regrasp by Learning to Place

Multimodal Virtual Point 3D Detection

LanguageRefer: Spatial-Language Model for 3D Visual Grounding

EfficientLPS: Efficient LiDAR Panoptic Segmentation

A Comparative Study of Coarse to Dense 3D Indoor Scene Registration Algorithms

StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Nonparametric Continuous Sensor Registration

Learning to Infer Kinematic Hierarchies for Novel Object Instances

Object DGCNN: 3D Object Detection using Dynamic Graphs

Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms

BuildingNet: Learning to Label 3D Buildings

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

A Learned Stereo Depth System for Robotic Manipulation in Homes

Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection

Fast and Accurate: Video Enhancement using Sparse Depth

UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry

PSE-Match: A Viewpoint-free Place Recognition Method with Parallel Semantic Embedding

Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery

Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles

Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study

Global Unifying Intrinsic Calibration for Spinning and Solid-State LiDARs