Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular ${d}$ epth ${e}$ stimation by ${v}$ irtual-world ${s}$ upervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision, and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Monocular Depth Estimation Through Virtual-World Supervision and Real-World SfM Self-Supervision


    Beteiligte:
    Gurram, Akhil (Autor:in) / Tuna, Ahmet Faruk (Autor:in) / Shen, Fengyi (Autor:in) / Urfalioglu, Onay (Autor:in) / Lopez, Antonio M. (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.08.2022


    Format / Umfang :

    3753956 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Monocular Fisheye Camera Depth Estimation Using Sparse LiDAR Supervision

    Kumar, Varun Ravi / Milz, Stefan / Witt, Christian et al. | IEEE | 2018


    Boosting Monocular 3D Object Detection With Object-Centric Auxiliary Depth Supervision

    Kim, Youngseok / Kim, Sanmin / Sim, Sangmin et al. | IEEE | 2023


    Real-Time Self-Supervised Monocular Depth Estimation Without GPU

    Poggi, Matteo / Tosi, Fabio / Aleotti, Filippo et al. | IEEE | 2022


    Supervision

    Wilkes, J.L. | Engineering Index Backfile | 1918


    Ship-shore collaborative yacht driver real-time supervision device and supervision method thereof

    CAI XIAOCHI / FANG XINNAN / GUI HAO et al. | Europäisches Patentamt | 2023

    Freier Zugriff