3D 视觉

CP$^3$: Channel Pruning Plug-in for Point-based Networks

Yaomin Huang, Ning Liu, Zhengping Che, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Guixu Zhang, Xinmei Liu, Feifei Feng, Jian Tang

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

Comments Yaomin Huang and Ning Liu are with equal contributions. This paper has been accepted by CVPR 2023

DepGraph: Towards Any Structural Pruning

Gongfan Fang, Xinyin Ma, Mingli Song, Michael Bi Mi, Xinchao Wang

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

Spherical Transformer for LiDAR-based 3D Recognition

Xin Lai, Yukang Chen, Fanbin Lu, Jianhui Liu, Jiaya Jia

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

Comments Accepted to CVPR 2023. Code is available at https://github.com/dvlab-research/SphereFormer.git

Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs

Masakazu Ohno, Riki Ukyo, Tatsuya Amano, Hamada Rizk, Hirozumi Yamaguchi

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

Comments Accepted to the 21st International Conference on Pervasive Computing and Communications (PerCom 2023)

Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication

Jinlong Li, Runsheng Xu, Xinyu Liu, Jin Ma, Zicheng Chi, Jiaqi Ma, Hongkai Yu

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

Comments this paper was accepted by IEEE Transactions on Intelligent Vehicles

Journal ref 2023 IEEE Transactions on Intelligent Vehicles

LoRCoN-LO: Long-term Recurrent Convolutional Network-based LiDAR Odometry

Donghwi Jung, Jae-Kyung Cho, Younghwa Jung, Soohyun Shin, Seong-Woo Kim

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

Comments 4 pages, ICEIC 2023

Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving

Yinpeng Dong, Caixin Kang, Jinlai Zhang, Zijian Zhu, Yikai Wang, Xiao Yang, Hang Su, Xingxing Wei, Jun Zhu

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

Comments CVPR 2023

Semantic 3D scene segmentation for robotic assembly process execution

Andreas Wiedholz, Stefanie Wucherer, Simon Dietrich

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

DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets

Haiyang Wang, Chen Shi, Shaoshuai Shi, Meng Lei, Sen Wang, Di He, Bernt Schiele, Liwei Wang

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

Comments Accepted by CVPR2023

MATE: Masked Autoencoders are Online 3D Test-Time Learners

M. Jehanzeb Mirza, Inkyu Shin, Wei Lin, Andreas Schriebl, Kunyang Sun, Jaesung Choe, Horst Possegger, Mateusz Kozinski, In So Kweon, Kun-Jin Yoon, Horst Bischof

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

Comments Code is available at this repository: https://github.com/jmiemirza/MATE

One-shot Learning for Autonomous Aerial Manipulation

Claudio Zito, Eliseo Ferrante

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

Comments aerial manipulation, aerial grasping, one-shot learning, collaborative transportation

Journal ref Frontiers in Robotics and AI, Sec. Computational Intelligence in Robotics, Volume 9, 2022

Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective

Xiaokang Chen, Jiaxiang Tang, Jingbo Wang, Gang Zeng

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

Comments Accepted to AAAI 2022

Planning for Multi-Object Manipulation with Graph Neural Network Relational Classifiers

Yixuan Huang, Adam Conkey, Tucker Hermans

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

Comments 10 pages, 7 figures, to be published in the proceedings of the IEEE Conference on Robotics and Automation (ICRA) 2023. Robot Demos: https://robot-learning.cs.utah.edu/project/graph_nets

CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP

Junbo Zhang, Runpei Dong, Kaisheng Ma

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

UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes

Sunwook Hwang, Youngseok Kim, Seongwon Kim, Saewoong Bahk, Hyung-Sin Kim

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

Comments We have updated the results to fix errors in the experimental process, which resulted in some logical changes. We also have added new experiments related to privacy protection. The previous version (v1) has been discarded

Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency

Runzhou Tao, Wencheng Han, Zhongying Qiu, Cheng-zhong Xu, Jianbing Shen

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

Comments CVPR 2023

MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving

Jiale Li, Hang Dai, Hao Han, Yong Ding

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

Comments Accepted to CVPR 2023 (preprint)

Optimized SC-F-LOAM: Optimized Fast LiDAR Odometry and Mapping Using Scan Context

Lizhou Liao, Chunyun Fu, Binbin Feng, Tian Su

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

Journal ref Proceedings of the 2022 6th CAA International Conference on Vehicular Control and Intelligence (CVCI), Nanjing, China, 28-30 October 2022

LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion

Xin Li, Tao Ma, Yuenan Hou, Botian Shi, Yuchen Yang, Youquan Liu, Xingjiao Wu, Qin Chen, Yikang Li, Yu Qiao, Liang He

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

Comments Accepted by CVPR2023

A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation

Lin Li, Wendong Ding, Yongkun Wen, Yufei Liang, Yong Liu, Guowei Wan

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

Comments 8 pages. Accepted by ICRA-2023

Modality-Agnostic Debiasing for Single Domain Generalization

Sanqing Qu, Yingwei Pan, Guang Chen, Ting Yao, Changjun Jiang, Tao Mei

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

Comments To appear in CVPR-2023

OSIS: Efficient One-stage Network for 3D Instance Segmentation

Chuan Tang, Xi Yang

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

UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion

Guancheng Chen, Junli Lin, Huabiao Qin

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

Comments 11 pages, 4 figures

Journal ref IEEE Transactions on Circuits and Systems for Video Technology, 2023

Combining visibility analysis and deep learning for refinement of semantic 3D building models by conflict classification

Olaf Wysocki, Eleonora Grilli, Ludwig Hoegner, Uwe Stilla

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

Comments ISPRS Annals, 3DGeoInfo 2022, Australia, Sydney

Journal ref ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-4/W2-2022

IC classifier: a classifier for 3D industrial components based on geometric prior using GNN

Zipeng Lin, Zhenguo Nie

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

Comments 15 pages including citations, 3 pages of figures

SLAMesh: Real-time LiDAR Simultaneous Localization and Meshing

Jianyuan Ruan, Bo Li, Yibo Wang, Yuxiang Sun

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

Comments Accepted by ICRA 2023. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data

Neng Wang, Chenghao Shi, Ruibin Guo, Huimin Lu, Zhiqiang Zheng, Xieyuanli Chen

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

Comments 8 pages, 4 figures, submitted

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

Jianren Wang, Haiming Gang, Siddharth Ancha, Yi-Ting Chen, David Held

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

Comments 3DV 2021

Dronument: System for Reliable Deployment of Micro Aerial Vehicles in Dark Areas of Large Historical Monuments

Pavel Petracek, Vit Kratky, Martin Saska

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

Journal ref IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 2078-2085, 2020

Histogram-based Deep Learning for Automotive Radar

Maxim Tatarchenko, Kilian Rambach

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