3D 视觉 - arXivDaily 专题

2108.10531 2021-10-12 cs.CV cs.AI cs.LG 57%

Unsupervised Depth Completion with Calibrated Backprojection Layers

Alex Wong, Stefano Soatto

专题命中点云：point cloud(abstract)；分类 cs.CV

2110.04081 2021-10-11 cs.CV cs.LG 57%

Flow Plugin Network for conditional generation

Patryk Wielopolski, Michał Koperski, Maciej Zięba

专题命中点云：point cloud(abstract)；分类 cs.CV

2110.03968 2021-10-11 cs.CV 57%

How to Build a Curb Dataset with LiDAR Data for Autonomous Driving

Dongfeng Bai, Tongtong Cao, Jingming Guo, Bingbing Liu

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 7 pages with 10 figures, submitted to 2022 IEEE International Conference on Robotics and Automation (ICRA)

2104.08230 2021-10-08 cs.CV 57%

Point-Based Modeling of Human Clothing

Ilya Zakharkin, Kirill Mazur, Artur Grigorev, Victor Lempitsky

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted for ICCV 2021

2103.08294 2021-10-05 cs.CV 57%

3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks

Aniruddha Ganguly, Tasin Ishmam, Khandker Aftarul Islam, Md Zahidur Rahman, Md. Shamsuzzoha Bayzid

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Contains 6 pages and 2 figures. Manuscript accepted and presented in the IEEE International Conference on Intelligent Robots and Systems (IROS) 2021

2107.05997 2021-10-04 cs.LG cs.CV stat.ML 57%

Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data

Sebastian Pölsterl, Christina Aigner, Christian Wachinger

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at 2021 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

2109.15033 2021-10-01 cs.CV 57%

Riedones3D: a celtic coin dataset for registration and fine-grained clustering

Sofiane Horache, Jean-Emmanuel Deschaud, François Goulette, Katherine Gruel, Thierry Lejars, Olivier Masson

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments The code and the dataset will be available on the 15th December 2021

2101.10747 2021-09-30 cs.CV eess.IV 57%

Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models

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

专题命中点云：point cloud(abstract)；分类 cs.CV

Journal ref 2021 IEEE International Conference on Image Processing (ICIP)

2012.09164 2021-09-28 cs.CV 57%

Point Transformer

Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

专题命中点云：point cloud(abstract)；分类 cs.CV

2105.11450 2021-09-23 cs.CV 57%

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

Zhengyuan Yang, Songyang Zhang, Liwei Wang, Jiebo Luo

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ICCV 2021 Oral

2109.09323 2021-09-21 cs.RO 57%

A Shadowcasting-Based Next-Best-View Planner for Autonomous 3D Exploration

Ana Batinovic, Antun Ivanovic, Tamara Petrovic, Stjepan Bogdan

专题命中点云：point cloud(abstract)；分类 cs.RO

2109.08553 2021-09-20 cs.CV 57%

Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck

Liyi Luo, Beiwen Tian, Hao Zhao, Guyue Zhou

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Code: https://github.com/OPEN-AIR-SUN/Viewpoint-Bottleneck

2109.08141 2021-09-17 cs.CV cs.AI cs.LG 57%

An End-to-End Transformer Model for 3D Object Detection

Ishan Misra, Rohit Girdhar, Armand Joulin

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at ICCV 2021

2108.10723 2021-09-16 cs.CV 57%

Improving 3D Object Detection with Channel-wise Transformer

Hualian Sheng, Sijia Cai, Yuan Liu, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Min-Jian Zhao

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ICCV2021

2106.03919 2021-09-16 cs.RO 57%

Learning to Detect Multi-Modal Grasps for Dexterous Grasping in Dense Clutter

Matt Corsaro, Stefanie Tellex, George Konidaris

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments IROS 2021 Accepted Version

2109.06526 2021-09-15 cs.CV 57%

Image-Based Alignment of 3D Scans

Dolores Messer, Jakob Wilm, Eythor R. Eiriksson, Vedrana A. Dahl, Anders B. Dahl

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 7 figures

2105.02020 2021-09-15 cs.RO 57%

Multi-Modal Loop Closing in Unstructured Planetary Environments with Visually Enriched Submaps

Riccardo Giubilato, Mallikarjuna Vayugundla, Wolfgang Stürzl, Martin J. Schuster, Armin Wedler, Rudolph Triebel

专题命中点云：point cloud(abstract)；分类 cs.RO

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

2011.02182 2021-09-15 cs.RO 57%

A Multi-Resolution Frontier-Based Planner for Autonomous 3D Exploration

Ana Batinović, Tamara Petrović, Antun Ivanovic, Frano Petric, Stjepan Bogdan

专题命中点云：point cloud(abstract)；分类 cs.RO

2109.05441 2021-09-14 cs.CV 57%

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception

Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by TPAMI 2021; Source code at https://github.com/xinge008/Cylinder3D. arXiv admin note: substantial text overlap with arXiv:2011.10033

2109.02497 2021-09-14 cs.CV 57%

Voxel Transformer for 3D Object Detection

Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments To appear at ICCV 2021

2109.04310 2021-09-10 cs.CV 57%

Deep Hough Voting for Robust Global Registration

Junha Lee, Seungwook Kim, Minsu Cho, Jaesik Park

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to ICCV 2021

2109.02499 2021-09-07 cs.CV 57%

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Jiageng Mao, Minzhe Niu, Haoyue Bai, Xiaodan Liang, Hang Xu, Chunjing Xu

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments To appear at ICCV 2021

2008.01918 2021-09-07 cs.CV 57%

Graph Signal Processing for Geometric Data and Beyond: Theory and Applications

Wei Hu, Jiahao Pang, Xianming Liu, Dong Tian, Chia-Wen Lin, Anthony Vetro

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at IEEE TMM

2109.01066 2021-09-03 cs.CV 57%

4D-Net for Learned Multi-Modal Alignment

AJ Piergiovanni, Vincent Casser, Michael S. Ryoo, Anelia Angelova

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ICCV 2021

2109.00918 2021-09-03 cs.CV cs.AI 57%

Multi-task learning from fixed-wing UAV images for 2D/3D city modeling

Mohammad R. Bayanlou, Mehdi Khoshboresh-Masouleh

专题命中点云：point cloud(abstract)；分类 cs.CV

Journal ref The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIV-M-3-2021, 2021, pp.1-5

2108.12863 2021-08-31 cs.CV 57%

MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection

Xun Tan, Xingyu Chen, Guowei Zhang, Jishiyu Ding, Xuguang Lan

专题命中点云：point cloud(abstract)；分类 cs.CV

2104.11181 2021-08-25 cs.CV 57%

H2O: Two Hands Manipulating Objects for First Person Interaction Recognition

Taein Kwon, Bugra Tekin, Jan Stuhmer, Federica Bogo, Marc Pollefeys

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to ICCV 2021

2108.10312 2021-08-24 cs.CV 57%

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving

Chenxu Luo, Xiaodong Yang, Alan Yuille

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments ICCV 2021

2108.08891 2021-08-23 cs.CV cs.LG 57%

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

Zihang Meng, Vikas Singh, Sathya N. Ravi

专题命中点云：point cloud(abstract)；分类 cs.CV

2108.08369 2021-08-20 cs.CV eess.IV 57%

Quality assessment of image matchers for DSM generation -- a comparative study based on UAV images

Rongjun Qin, Armin Gruen, Cive Fraser

专题命中点云：point cloud(abstract)；分类 cs.CV

1. 点云 7730 篇

Unsupervised Depth Completion with Calibrated Backprojection Layers

Flow Plugin Network for conditional generation

How to Build a Curb Dataset with LiDAR Data for Autonomous Driving

Point-Based Modeling of Human Clothing

3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks

Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data

Riedones3D: a celtic coin dataset for registration and fine-grained clustering

Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models

Point Transformer

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

A Shadowcasting-Based Next-Best-View Planner for Autonomous 3D Exploration

Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneck

An End-to-End Transformer Model for 3D Object Detection

Improving 3D Object Detection with Channel-wise Transformer

Learning to Detect Multi-Modal Grasps for Dexterous Grasping in Dense Clutter

Image-Based Alignment of 3D Scans

Multi-Modal Loop Closing in Unstructured Planetary Environments with Visually Enriched Submaps

A Multi-Resolution Frontier-Based Planner for Autonomous 3D Exploration

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception

Voxel Transformer for 3D Object Detection

Deep Hough Voting for Robust Global Registration

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Graph Signal Processing for Geometric Data and Beyond: Theory and Applications

4D-Net for Learned Multi-Modal Alignment

Multi-task learning from fixed-wing UAV images for 2D/3D city modeling

MBDF-Net: Multi-Branch Deep Fusion Network for 3D Object Detection

H2O: Two Hands Manipulating Objects for First Person Interaction Recognition

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

Quality assessment of image matchers for DSM generation -- a comparative study based on UAV images