Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

被引:84
|
作者
Qin, Zengyi [1 ]
Wang, Jinglu [2 ]
Lu, Yan [2 ]
机构
[1] Tsinghua Univ, Beijing, Peoples R China
[2] Microsoft Res, Beijing, Peoples R China
关键词
D O I
10.1109/CVPR.2019.00780
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing 3D anchors to explicitly construct object-level correspondences between the regions of interest in stereo images, from which the deep neural network learns to detect and triangulate the targeted object in 3D space. We also introduce a cost-efficient channel reweighting strategy that enhances representational features and weakens noisy signals to facilitate the learning process. All of these are flexibly integrated into a solid baseline detector that uses monocular images. We demonstrate that both the monocular baseline and the stereo triangulation learning network outperform the prior state-of-the-arts in 3D object detection and localization on the challenging KITTI dataset.
引用
收藏
页码:7607 / 7615
页数:9
相关论文
共 50 条
  • [31] PLUMENet: Efficient 3D Object Detection from Stereo Images
    Wang, Yan
    Yang, Bin
    Hu, Rui
    Liang, Ming
    Urtasun, Raquel
    2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 3383 - 3390
  • [32] 3D Street Object Detection from Monocular Images Using Deep Learning and Depth Information
    Liu, Wei
    Zhang, Tao
    Ma, Yun
    Wei, Longsheng
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2023, 27 (02) : 198 - 206
  • [33] 3D Object Detection Based on Proposal Generation Network Utilizing Monocular Images
    ul Haq, Qazi Mazhar
    Haq, Muhamad Amirul
    Ruan, Shanq-Jang
    Liang, Pei-Jung
    Gao, De-Qin
    IEEE CONSUMER ELECTRONICS MAGAZINE, 2022, 11 (05) : 47 - 53
  • [34] Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
    Hong, Yu
    Dai, Hang
    Ding, Yong
    COMPUTER VISION, ECCV 2022, PT X, 2022, 13670 : 87 - 104
  • [35] A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection
    Kim, Seong-heum
    Hwang, Youngbae
    ELECTRONICS, 2021, 10 (04) : 1 - 22
  • [36] Object-Centric Stereo Matching for 3D Object Detection
    Pon, Alex D.
    Ku, Jason
    Li, Chengyao
    Waslander, Steven L.
    2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 8383 - 8389
  • [37] Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
    Liu, Xianpeng
    Zheng, Ce
    Cheng, Kelvin
    Xue, Nan
    Qi, Guo-Jun
    Wu, Tianfu
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 6413 - 6423
  • [38] Progressive Coordinate Transforms for Monocular 3D Object Detection
    Wang, Li
    Zhang, Li
    Zhu, Yi
    Zhang, Zhi
    He, Tong
    Li, Mu
    Xue, Xiangyang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [39] Exploring Geometric Consistency for Monocular 3D Object Detection
    Lian, Qing
    Ye, Botao
    Xu, Ruijia
    Yao, Weilong
    Zhang, Tong
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1675 - 1684
  • [40] Monocular 3D Object Detection With Motion Feature Distillation
    Hu, Henan
    Li, Muyu
    Zhu, Ming
    Gao, Wen
    Liu, Peiyu
    Chan, Kwok-Leung
    IEEE ACCESS, 2023, 11 : 82933 - 82945