In this paper, a complete pipeline for image-based 3D reconstruction of urban scenarios is proposed, based on PatchMatch Multi-View Stereo (MVS). Input images are firstly fed into an off-the-shelf visual SLAM system to extract camera poses and sparse keypoints, which are used to initialize PatchMatch optimization. Then, pixelwise depths and normals are iteratively computed in a multi-scale framework with a novel depth-normal consistency loss term and a global refinement algorithm to balance the inherently local nature of PatchMatch. Finally, a large-scale point cloud is generated by back-projecting multi-view consistent estimates in 3D. The proposed approach is carefully evaluated against both classical MVS algorithms and monocular depth networks on the KITTI dataset, showing state of the art performances.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction


    Contributors:


    Publication date :

    2022-06-05


    Size :

    1186063 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast PatchMatch Stereo Matching Using Multi-Scale Cost Fusion for Automotive Applications

    Cho, Ji-Ho / Humenberger, Martin | British Library Conference Proceedings | 2015



    Multi-view Superpixel Stereo in Urban Environments

    Mi?ušík, B. / Košecká, J. | British Library Online Contents | 2010


    PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation

    Besse, F. / Rother, C. / Fitzgibbon, A. et al. | British Library Online Contents | 2014


    Speeding up 3D speckle tracking using PatchMatch [9784-140]

    British Library Conference Proceedings | 2016