Projects

  1. summary image

    DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

    Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu

    Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the ...

    Continue reading

    Keywords: 3D Object Detection

Publications

2022

  • DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
    Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu
    In Proceeding of European Conference on Computer Vision (ECCV 2022), Tel-Aviv, Israel, Oct. 2022
    Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code
    • @inproceedings{ deviant-depth-equivariant-network-for-monocular-3d-object-detection,
      author = { Abhinav Kumar and Garrick Brazil and Enrique Corona and Armin Parchami and Xiaoming Liu },
      title = { DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection },
      booktitle = { In Proceeding of European Conference on Computer Vision },
      address = { Tel-Aviv, Israel },
      month = { October },
      year = { 2022 },
    }