Learning to adapt for stereo

Alessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi DI Stefano, Thalaiyasingam Ajanthan, Philip H.S. Torr

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    65 Citations (Scopus)

    Abstract

    Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in the environment, making them less suitable for practical applications such as autonomous driving. In this work, we introduce a "learning-to-adapt" framework that enables deep stereo methods to continuously adapt to new target domains in an unsupervised manner. Specifically, our approach incorporates the adaptation procedure into the learning objective to obtain a base set of parameters that are better suited for unsupervised online adaptation. To further improve the quality of the adaptation, we learn a confidence measure that effectively masks the errors introduced during the unsupervised adaptation. We evaluate our method on synthetic and real-world stereo datasets and our experiments evidence that learning-to-adapt is, indeed beneficial for online adaptation on vastly different domains.

    Original languageEnglish
    Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
    PublisherIEEE Computer Society
    Pages9653-9662
    Number of pages10
    ISBN (Electronic)9781728132938
    DOIs
    Publication statusPublished - Jun 2019
    Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
    Duration: 16 Jun 201920 Jun 2019

    Publication series

    NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    Volume2019-June
    ISSN (Print)1063-6919

    Conference

    Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
    Country/TerritoryUnited States
    CityLong Beach
    Period16/06/1920/06/19

    Fingerprint

    Dive into the research topics of 'Learning to adapt for stereo'. Together they form a unique fingerprint.

    Cite this