Semi-supervised Depth Estimation

Semi-Supervised Depth Estimation is a depth estimation method that leverages both labeled and unlabeled data during training, distinguishing itself from fully supervised and unsupervised approaches by combining sparse ground truth depth information with data-driven learning from unlabeled sequences to improve depth prediction accuracy.

17

Publications

1.3K

Citations

66

Authors

24

Institutions

Publications per year

2017–2026

17

Authors

66

  1. AG
    Adrien Gaidon

    Toyota Research Institute

    2 publications · 59 citations

    2

    h-index

  2. RA
    Rareş Ambruş

    Toyota Research Institute

    2 publications · 59 citations

    2

    h-index

  3. VG
    Vitor Guizilini

    The University of Sydney, Australia

    2 publications · 59 citations

    2

    h-index

  4. JS
    Jörg Stückler

    University of Bonn, Germany

    2 publications · 778 citations

    2

    h-index

  5. YK
    Yevhen Kuznietsov

    KU Leuven, Belgium

    2 publications · 778 citations

    2

    h-index

1–5 of 66

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 151 citations

    4

    h-index

  2. 1

    h-index

  3. Science China Technological Sciences

    1 publications · 10 citations

    1

    h-index

  4. IEEE Access

    1 publications · 30 citations

    1

    h-index

  5. Journal of Intelligent & Robotic Systems

    1 publications · 17 citations

    1

    h-index

1–5