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
  • [21] Learning Depth-Guided Convolutions for Monocular 3D Object Detection
    Ng, Mingyu
    Huo, Yuqi
    Yi, Hongwei
    Wang, Zhe
    Shi, Jianping
    Lu, Zhiwu
    Luo, Ping
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 4306 - 4315
  • [22] Monocular 3D Object Detection Utilizing Auxiliary Learning With Deformable Convolution
    Chen, Jiun-Han
    Shieh, Jeng-Lun
    Haq, Muhamad Amirul
    Ruan, Shanq-Jang
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (03) : 2424 - 2436
  • [23] Monocular 3D Object Detection for Autonomous Driving
    Chen, Xiaozhi
    Kundu, Kaustav
    Zhang, Ziyu
    Ma, Huimin
    Fidler, Sanja
    Urtasun, Raquel
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 2147 - 2156
  • [24] Dimension Embeddings for Monocular 3D Object Detection
    Zhang, Yunpeng
    Zheng, Wenzhao
    Zhu, Zheng
    Huang, Guan
    Du, Dalong
    Zhou, Jie
    Lu, Jiwen
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1579 - 1588
  • [25] ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection
    Gao, Aqi
    Pang, Yanwei
    Nie, Jing
    Shao, Zhuang
    Cao, Jiale
    Guo, Yishun
    Li, Xuelong
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (04) : 2000 - 2009
  • [26] Multivariate Probabilistic Monocular 3D Object Detection
    Shi, Xuepeng
    Chen, Zhixiang
    Kim, Tae-Kyun
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 4270 - 4279
  • [27] Uncertainty Prediction for Monocular 3D Object Detection
    Mun, Junghwan
    Choi, Hyukdoo
    SENSORS, 2023, 23 (12)
  • [28] Monocular 3D object detection for distant objects
    Li, Jiahao
    Han, Xiaohong
    JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (03) : 33021
  • [29] Homography Loss for Monocular 3D Object Detection
    Gu, Jiaqi
    Wu, Bojian
    Fan, Lubin
    Huang, Jianqiang
    Cao, Shen
    Xiang, Zhiyu
    Hua, Xian-Sheng
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1070 - 1079
  • [30] M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
    Brazil, Garrick
    Liu, Xiaoming
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9286 - 9295