3D 视觉 - arXivDaily 专题

2208.02483 2022-11-04 cs.CV 57%

Semantic Segmentation of Fruits on Multi-sensor Fused Data in Natural Orchards

Hanwen Kang, Xing Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

2211.01093 2022-11-03 cs.CV eess.IV 57%

Improving transferability of 3D adversarial attacks with scale and shear transformations

Jinali Zhang, Yinpeng Dong, Jun Zhu, Jihong Zhu, Minchi Kuang, Xiaming Yuan

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 10 pages

2211.00312 2022-11-02 cs.CV cs.LG 57%

HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar

Yanyan Huang, Yong Wang, Kun Shi, Chaojie Gu, Yu Fu, Cheng Zhuo, Zhiguo Shi

专题命中点云：point cloud(abstract)；分类 cs.CV

2211.00207 2022-11-02 cs.CV 57%

GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection

Xiaoshui Huang, Wentao Qu, Yifan Zuo, Yuming Fang, Xiaowei Zhao

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by IEEE RAL

2210.16815 2022-11-01 cs.CV 57%

CAD 3D Model classification by Graph Neural Networks: A new approach based on STEP format

L. Mandelli, S. Berretti

专题命中点云：point cloud(abstract)；分类 cs.CV

2210.15365 2022-10-28 cs.CV cs.LG 57%

Li3DeTr: A LiDAR based 3D Detection Transformer

Gopi Krishna Erabati, Helder Araujo

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023

2203.00871 2022-10-28 cs.CV 57%

Dense Voxel Fusion for 3D Object Detection

Anas Mahmoud, Jordan S. K. Hu, Steven L. Waslander

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted in WACV 2023

2210.14897 2022-10-27 cs.CV 57%

Searching Dense Point Correspondences via Permutation Matrix Learning

Zhiyuan Zhang, Jiadai Sun, Yuchao Dai, Bin Fan, Qi Liu

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to IEEE Signal Processing Letters (SPL) 2022

2210.10983 2022-10-27 cs.CV cs.AI 57%

PSA-Det3D: Pillar Set Abstraction for 3D object Detection

Zhicong Huang, Jingwen Zhao, Zhijie Zheng, Dihu Chena, Haifeng Hu

专题命中点云：point cloud(abstract)；分类 cs.CV

2210.13488 2022-10-26 cs.CV 57%

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Zhaoqi Leng, Guowang Li, Chenxi Liu, Ekin Dogus Cubuk, Pei Sun, Tong He, Dragomir Anguelov, Mingxing Tan

专题命中点云：point cloud(abstract)；分类 cs.CV

2006.04569 2022-10-26 cs.CV 57%

Parameter-Efficient Person Re-identification in the 3D Space

Zhedong Zheng, Nenggan Zheng, Yi Yang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments The code is available at https://github.com/layumi/person-reid-3d

Journal ref IEEE Transactions on Neural Networks and Learning Systems (2022)

2210.12209 2022-10-25 cs.RO cs.AI 57%

Motion Policy Networks

Adam Fishman, Adithyavairan Murali, Clemens Eppner, Bryan Peele, Byron Boots, Dieter Fox

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments To be published in the Conference on Robot Learning (CoRL) 2022. 10 pages with 4 figures. Appendix has 10 pages and 1 figure

2210.09615 2022-10-19 cs.CV 57%

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

Xin Li, Botian Shi, Yuenan Hou, Xingjiao Wu, Tianlong Ma, Yikang Li, Liang He

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by ECCV 2022

2210.08114 2022-10-18 quant-ph cs.CV cs.LG 57%

QuAnt: Quantum Annealing with Learnt Couplings

Marcel Seelbach Benkner, Maximilian Krahn, Edith Tretschk, Zorah Lähner, Michael Moeller, Vladislav Golyanik

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments incl. appendix

2209.01170 2022-10-18 cs.CV cs.LG 57%

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data

Mao Ye, Lemeng Wu, Qiang Liu

专题命中点云：point cloud(abstract)；分类 cs.CV

2207.04221 2022-10-18 cs.CV 57%

Learning to Register Unbalanced Point Pairs

Kanghee Lee, Junha Lee, Jaesik Park

专题命中点云：point cloud(abstract)；分类 cs.CV

2210.07577 2022-10-17 cs.CV 57%

MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation

Andra Petrovai, Sergiu Nedevschi

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments WACV 2023

2210.07424 2022-10-17 cs.CV 57%

Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

YuXuan Liu, Nikhil Mishra, Maximilian Sieb, Yide Shentu, Pieter Abbeel, Xi Chen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments In ECCV 2022. Code and dataset are available at https://bbox.yuxuanliu.com

2206.04670 2022-10-14 cs.CV cs.AI 57%

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Abed Al Kader Hammoud, Mohamed Elhoseiny, Bernard Ghanem

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by NeurIPS'22. Code and models are available at https://github.com/guochengqian/pointnext

2206.00630 2022-10-14 cs.CV 57%

Unifying Voxel-based Representation with Transformer for 3D Object Detection

Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian Sun, Jiaya Jia

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2022

2210.05666 2022-10-13 cs.CV 57%

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted at NeurIPS 2022

2210.05534 2022-10-12 cs.CV 57%

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

Linghua Tang, Le Hui, Jin Xie

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments accepted by ACCV 2022

2210.04801 2022-10-11 cs.CV 57%

4D Unsupervised Object Discovery

Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2022. 17 pages, 6 figures

2210.03954 2022-10-11 cs.CV 57%

Contact-aware Human Motion Forecasting

Wei Mao, Miaomiao Liu, Richard Hartley, Mathieu Salzmann

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted to NeurIPS2022

2210.03331 2022-10-10 cs.CV 57%

Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling

Daeun Lee, Jongwon Park, Jinkyu Kim

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 10 pages

2206.01772 2022-10-10 cs.CV cs.AI 57%

Radar Guided Dynamic Visual Attention for Resource-Efficient RGB Object Detection

Hemant Kumawat, Saibal Mukhopadhyay

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted in International Joint Conference on Neural Networks (IJCNN) 2022

Journal ref 2022 International Joint Conference on Neural Networks (IJCNN)

2210.03118 2022-10-07 cs.CV 57%

Unsupervised confidence for LiDAR depth maps and applications

Andrea Conti, Matteo Poggi, Filippo Aleotti, Stefano Mattoccia

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments IROS 2022. Code available at https://github.com/andreaconti/lidar-confidence

2203.08479 2022-10-07 cs.CV 57%

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

Ping-Chung Yu, Cheng Sun, Min Sun

专题命中点云：point cloud(abstract)；分类 cs.CV

2210.02060 2022-10-06 cs.CV cs.LG 57%

Graph Classification via Discriminative Edge Feature Learning

Yang Yi, Xuequan Lu, Shang Gao, Antonio Robles-Kelly, Yuejie Zhang

专题命中点云：point cloud(abstract)；分类 cs.CV

2103.10997 2022-10-06 cs.RO 57%

MVGrasp: Real-Time Multi-View 3D Object Grasping in Highly Cluttered Environments

Hamidreza Kasaei, Mohammadreza Kasaei

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments The video of our experiments can be found here: https://youtu.be/c-4lzjbF7fY

1. 点云 7723 篇

Semantic Segmentation of Fruits on Multi-sensor Fused Data in Natural Orchards

Improving transferability of 3D adversarial attacks with scale and shear transformations

HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar

GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection

CAD 3D Model classification by Graph Neural Networks: A new approach based on STEP format

Li3DeTr: A LiDAR based 3D Detection Transformer

Dense Voxel Fusion for 3D Object Detection

Searching Dense Point Correspondences via Permutation Matrix Learning

PSA-Det3D: Pillar Set Abstraction for 3D object Detection

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Parameter-Efficient Person Re-identification in the 3D Space

Motion Policy Networks

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

QuAnt: Quantum Annealing with Learnt Couplings

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data

Learning to Register Unbalanced Point Pairs

MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation

Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

Unifying Voxel-based Representation with Transformer for 3D Object Detection

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

4D Unsupervised Object Discovery

Contact-aware Human Motion Forecasting

Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling

Radar Guided Dynamic Visual Attention for Resource-Efficient RGB Object Detection

Unsupervised confidence for LiDAR depth maps and applications

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

Graph Classification via Discriminative Edge Feature Learning

MVGrasp: Real-Time Multi-View 3D Object Grasping in Highly Cluttered Environments