Unsupervised learning methods have achieved remarkable performance in monocular depth estimation and camera pose, which mostly solve the multi-task learning problem by using their inner geometry consistency as the self-supervision signal. While most existing approaches mostly adopt the generative model to obtain the depth map prediction, so in the resolution of depth map there is room for improvement. To this end, we present our unsupervised learning architecture based on adversarial learning model, which is used for unsupervised learning of high-resolution single view depth and camera pose. Specifically, we present a multi-scale deep convolutional Generative Adversarial Network (GAN) based learning system, which consists of three networks (pose estimation network PCNN, Generator-D and Discriminator-D for depth map prediction). Furthermore, in order to generate high-resolution depth map, we propose a multi-scale GAN model (MSGAN) to decompose the hard high-quality image generation problem into more manageable sub-problems through a coarse-to-fine process. Then, we modify the overall generation architecture of GAN model by changing the down-sampling and up-sampling components to improve the quality and accuracy of the depth map prediction. Finally, in order to improve the rate of convergence, we use the Least Square Error to increase the penalty for outliers. Detailed quantitative and qualitative evaluations of the proposed framework on the KITTI dataset show that the proposed method provides better results for both pose estimation and depth recovery.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Unsupervised Learning of Depth Estimation and Camera Pose With Multi-Scale GANs


    Beteiligte:
    Xu, Yufan (Autor:in) / Wang, Yan (Autor:in) / Huang, Rui (Autor:in) / Lei, Zeyu (Autor:in) / Yang, Junyao (Autor:in) / Li, Zijian (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-10-01


    Format / Umfang :

    2659492 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multi-camera head pose estimation

    Muñoz-Salinas, R. / Yeguas-Bolivar, E. / Saffiotti, A. et al. | British Library Online Contents | 2012


    SYSTEM AND METHOD TO IMPROVE MULTI-CAMERA MONOCULAR DEPTH ESTIMATION USING POSE AVERAGING

    GUIZILINI VITOR / AMBRUS RARES ANDREI / GAIDON ADRIEN DAVID et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry

    Wang, Guangming / Zhang, Chi / Wang, Hesheng et al. | IEEE | 2022


    System and method to improve multi-camera monocular depth estimation using pose averaging

    GUIZILINI VITOR / AMBRUS RARES ANDREI / GAIDON ADRIEN DAVID et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    SCALE-AWARE DEPTH ESTIMATION USING MULTI-CAMERA PROJECTION LOSS

    GUIZILINI VITOR / AMBRUS RARES ANDREI / GAIDON ADRIEN DAVID et al. | Europäisches Patentamt | 2022

    Freier Zugriff