Stereo matching aiming to perceive the 3-D geometry of a scene facilitates numerous computer vision tasks used in advanced driver assistance systems (ADAS). Although numerous methods have been proposed for this task by leveraging deep convolutional neural networks (CNNs), stereo matching still remains an unsolved problem due to its inherent matching ambiguities. To overcome these limitations, we present a method for jointly estimating disparity and confidence from stereo image pairs through deep networks. We accomplish this through a minmax optimization to learn the generative cost aggregation networks and discriminative confidence estimation networks in an adversarial manner. Concretely, the generative cost aggregation networks are trained to accurately generate disparities at both confident and unconfident pixels from an input matching cost that are indistinguishable by the discriminative confidence estimation networks, while the discriminative confidence estimation networks are trained to distinguish the confident and unconfident disparities. In addition, to fully exploit complementary information of matching cost, disparity, and color image in confidence estimation, we present a dynamic fusion module. Experimental results show that this model outperforms the state-of-the-art methods on various benchmarks including real driving scenes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Adversarial Confidence Estimation Networks for Robust Stereo Matching


    Beteiligte:
    Kim, Sunok (Autor:in) / Min, Dongbo (Autor:in) / Kim, Seungryong (Autor:in) / Sohn, Kwanghoon (Autor:in)


    Erscheinungsdatum :

    2021-11-01


    Format / Umfang :

    24329962 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Stereo Depth Estimation: A Confidence Interval Approach

    Mandelbaum, R. / Kamberova, G. / Mintz, M. et al. | British Library Conference Proceedings | 1998


    Deep Confidence Propagation Stereo Network

    Zeng, Kai / Wang, Yaonan / Wang, Wei et al. | IEEE | 2023


    Bayesian stereo matching

    Cheng, L. / Caelli, T. | British Library Online Contents | 2007


    Robust stereo matching using adaptive random walk with restart algorithm

    Lee, S. / Lee, J. H. / Lim, J. et al. | British Library Online Contents | 2015


    Adaptive stereo similarity fusion using confidence measures

    Saygili, G. / van der Maaten, L. / Hendriks, E. A. | British Library Online Contents | 2015