Corpus ID: 227162553

Unsupervised Object Detection with LiDAR Clues

@article{Tian2020UnsupervisedOD,
  title={Unsupervised Object Detection with LiDAR Clues},
  author={Hao Tian and Yuntao Chen and Jifeng Dai and Zhaoxiang Zhang and X. Zhu},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.12953}
}
  • Hao Tian, Yuntao Chen, +2 authors X. Zhu
  • Published 2020
  • Computer Science
  • ArXiv
  • Despite the importance of unsupervised object detection, to the best of our knowledge, there is no previous work addressing this problem. One main issue, widely known to the community, is that object boundaries derived only from 2D image appearance are ambiguous and unreliable. To address this, we exploit LiDAR clues to aid unsupervised object detection. By exploiting the 3D scene structure, the issue of localization can be considerably mitigated. We further identify another major issue, seldom… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 109 REFERENCES
    RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement
    • 70
    • PDF
    Solving Missing-Annotation Object Detection with Background Recalibration Loss
    • 2
    • PDF
    Fast Lidar Clustering by Density and Connectivity
    • 2
    Consistency-based Semi-supervised Learning for Object detection
    • 29
    • PDF
    Missing Labels in Object Detection
    • 7
    • PDF
    Joint 3D Proposal Generation and Object Detection from View Aggregation
    • 475
    • PDF
    PointPillars: Fast Encoders for Object Detection From Point Clouds
    • 368
    • PDF
    BirdNet: A 3D Object Detection Framework from LiDAR Information
    • 82
    • PDF
    STD: Sparse-to-Dense 3D Object Detector for Point Cloud
    • 129
    • PDF
    Efficient Online Segmentation for Sparse 3D Laser Scans
    • 36