3D 视觉 - arXivDaily 专题

2212.03504 2023-01-20 cs.CV cs.AI 57%

LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving

Xiang Li, Junbo Yin, Botian Shi, Yikang Li, Ruigang Yang, Jianbing Shen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments AAAI2023

2301.07499 2023-01-19 cs.CV 57%

A Comprehensive Review of Modern Object Segmentation Approaches

Yuanbo Wang, Unaiza Ahsan, Hanyan Li, Matthew Hagen

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 173 pages, 49 figures, published in Foundations and Trends in Computer Graphics and Vision on 10/4/22. Authors retain copyright

Journal ref Foundations and Trends in Computer Graphics and Vision: Vol. 13: No. 2-3, pp 111-283

2301.05027 2023-01-13 cs.CV 57%

SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning

Chengzhi Wu, Linxi Qiu, Kanran Zhou, Julius Pfrommer, Jürgen Beyerer

专题命中点云：point cloud(abstract)；分类 cs.CV

2301.04058 2023-01-11 cs.CV cs.AI 57%

Rethinking Voxelization and Classification for 3D Object Detection

Youshaa Murhij, Alexander Golodkov, Dmitry Yudin

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted in ICONIP 2022. arXiv admin note: text overlap with arXiv:1902.06326 by other authors

2301.03956 2023-01-11 cs.RO 57%

Towards High-Definition Maps: a Framework Leveraging Semantic Segmentation to Improve NDT Map Compression and Descriptivity

Petri Manninen, Heikki Hyyti, Ville Kyrki, Jyri Maanpää, Josef Taher, Juha Hyyppä

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 8 pages, 8 figures, IROS22

2301.03580 2023-01-11 cs.CV cs.AI cs.LG 57%

Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Keyu Tian, Yi Jiang, Qishuai Diao, Chen Lin, Liwei Wang, Zehuan Yuan

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments v2: fixed some formatting errors

2106.09637 2023-01-05 cs.CV 57%

AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition

Tiago Barros, Luís Garrote, Ricardo Pereira, Cristiano Premebida, Urbano J. Nunes

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in ROBOT 2022: Fifth Iberian Robotics Conference, and is available online at https://doi.org/10.1007/978-3-031-21065-5_26

2301.00527 2023-01-03 cs.CV 57%

Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data

Jumin Lee, Woobin Im, Sebin Lee, Sung-Eui Yoon

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.14138 2023-01-02 cs.RO 57%

Planning Paths through Occlusions in Urban Environments

Yutao Han, Youya Xia, Guo-Jun Qi, Mark Campbell

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments 10 pages (2 for references), 3 figures, 3 Tables, Conference on Robot Learning 2022 (CoRL)

2212.13218 2022-12-27 cs.RO 57%

Multisensor Data Fusion for Reliable Obstacle Avoidance

Thanh Nguyen Canh, Truong Son Nguyen, Cong Hoang Quach, Xiem HoangVan, Manh Duong Phung

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments In the 11th International Conference on Control, Automation and Information Sciences (ICCAIS 2022), Hanoi, Vietnam

2207.00195 2022-12-27 cs.RO 57%

Learning Diverse and Physically Feasible Dexterous Grasps with Generative Model and Bilevel Optimization

Albert Wu, Michelle Guo, C. Karen Liu

专题命中点云：point cloud(abstract)；分类 cs.RO

2212.00442 2022-12-22 cs.CV 57%

MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection

Junho Koh, Junhyung Lee, Youngwoo Lee, Jaekyum Kim, Jun Won Choi

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI'23)

2112.11088 2022-12-21 cs.CV 57%

EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

Zhe Liu, Tengteng Huang, Bingling Li, Xiwu Chen, Xi Wang, Xiang Bai

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by TPAMI-2022

2212.05743 2022-12-20 cs.RO 57%

A Light-Weight LiDAR-Inertial SLAM System with Loop Closing

Kangcheng Liu, Huosen Ou

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments ICARM 2022

2212.09273 2022-12-20 cs.CV 57%

Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection

Cheng-Ju Ho, Chen-Hsuan Tai, Yi-Hsuan Tsai, Yen-Yu Lin, Ming-Hsuan Yang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments BMVC2022

2209.14169 2022-12-20 cs.CV cs.AI cs.MM 57%

CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention

Ziyu Guo, Renrui Zhang, Longtian Qiu, Xianzheng Ma, Xupeng Miao, Xuming He, Bin Cui

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by AAAI 2023, 12 pages, 6 figures

2210.09213 2022-12-15 cs.CV cs.LG 57%

Segmentation-guided Domain Adaptation for Efficient Depth Completion

Fabian Märkert, Martin Sunkel, Anselm Haselhoff, Stefan Rudolph

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.06785 2022-12-14 cs.CV cs.AI 57%

Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders

Renrui Zhang, Liuhui Wang, Yu Qiao, Peng Gao, Hongsheng Li

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.06682 2022-12-14 cs.CV 57%

Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation

Chaolong Yang, Yuyao Yan, Weiguang Zhao, Jianan Ye, Xi Yang, Amir Hussain, Kaizhu Huang

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.05477 2022-12-13 cs.RO 57%

3D LiDAR Aided GNSS NLOS Mitigation for Reliable GNSS-RTK Positioning in Urban Canyons

Xikun Liu, Weisong Wen, Feng Huang, Han Gao, Yongliang Wang, Li-Ta Hsu

专题命中点云：point cloud(abstract)；分类 cs.RO

2212.02755 2022-12-08 cs.CV cs.AI 57%

Objects as Spatio-Temporal 2.5D points

Paridhi Singh, Gaurav Singh, Arun Kumar

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.02085 2022-12-07 cs.RO 57%

RGB-L: Enhancing Indirect Visual SLAM using LiDAR-based Dense Depth Maps

Florian Sauerbeck, Benjamin Obermeier, Martin Rudolph, Johannes Betz

专题命中点云：point cloud(abstract)；分类 cs.RO

Comments Accepted at ICCCR 2023

2111.06091 2022-12-07 cs.CV 57%

A Survey of Visual Transformers

Yang Liu, Yao Zhang, Yixin Wang, Feng Hou, Jin Yuan, Jiang Tian, Yang Zhang, Zhongchao Shi, Jianping Fan, Zhiqiang He

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

2212.02057 2022-12-06 cs.CV cs.AI eess.IV 57%

DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection

Ziyuan Zhao, Mingxi Xu, Peisheng Qian, Ramanpreet Singh Pahwa, Richard Chang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by the 33rd British Machine Vision Conference (BMVC 2022)

Journal ref 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. BMVA Press, 2022. URL https://bmvc2022.mpi-inf.mpg.de/0916.pdf

2212.00920 2022-12-06 cs.CV 57%

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

Yinghong Liao, Wending Zhou, Xu Yan, Shuguang Cui, Yizhou Yu, Zhen Li

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments AAAI 2023

2212.00987 2022-12-05 cs.CV 57%

Sparse SPN: Depth Completion from Sparse Keypoints

Yuqun Wu, Jae Yong Lee, Derek Hoiem

专题命中点云：point cloud(abstract)；分类 cs.CV

2212.00928 2022-12-05 cs.CV 57%

Single-shot ToF sensing with sub-mm precision using conventional CMOS sensors

Manuel Ballester, Heming Wang, Jiren Li, Oliver Cossairt, Florian Willomitzer

专题命中点云：point cloud(abstract)；分类 cs.CV

2203.09167 2022-12-05 cs.CV 57%

Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion

Jean Pierre Richa, Jean-Emmanuel Deschaud, François Goulette, Nicolas Dalmasso

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 8 pages, 7 figures, 5 tables

2212.00262 2022-12-02 cs.CV cs.LG eess.IV 57%

Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery

Yisi Luo, Xile Zhao, Zhemin Li, Michael K. Ng, Deyu Meng

专题命中点云：point cloud(abstract)；分类 cs.CV

2211.11962 2022-12-02 cs.CV 57%

Transformation-Equivariant 3D Object Detection for Autonomous Driving

Hai Wu, Chenglu Wen, Wei Li, Xin Li, Ruigang Yang, Cheng Wang

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments Accepted by AAAI 2023

1. 点云 7723 篇

LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving

A Comprehensive Review of Modern Object Segmentation Approaches

SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning

Rethinking Voxelization and Classification for 3D Object Detection

Towards High-Definition Maps: a Framework Leveraging Semantic Segmentation to Improve NDT Map Compression and Descriptivity

Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition

Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data

Planning Paths through Occlusions in Urban Environments

Multisensor Data Fusion for Reliable Obstacle Avoidance

Learning Diverse and Physically Feasible Dexterous Grasps with Generative Model and Bilevel Optimization

MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection

EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection

A Light-Weight LiDAR-Inertial SLAM System with Loop Closing

Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection

CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention

Segmentation-guided Domain Adaptation for Efficient Depth Completion

Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders

Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation

3D LiDAR Aided GNSS NLOS Mitigation for Reliable GNSS-RTK Positioning in Urban Canyons

Objects as Spatio-Temporal 2.5D points

RGB-L: Enhancing Indirect Visual SLAM using LiDAR-based Dense Depth Maps

A Survey of Visual Transformers

DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

Sparse SPN: Depth Completion from Sparse Keypoints

Single-shot ToF sensing with sub-mm precision using conventional CMOS sensors

Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion

Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery

Transformation-Equivariant 3D Object Detection for Autonomous Driving