Journal of Applied Optics, Volume. 43, Issue 3, 436(2022)

Patch-match binocular 3D reconstruction based on deep learning

Lizheng SONG, Dongyun LIN, Xiafu PENG, and Tengfei LIU
Author Affiliations
  • School of Aeronautics and Astronautics, Xiamen University, Xiamen 361005, China
  • show less

    The patch-match algorithm has been widely used in binocular stereo reconstruction due to its low memory consumption and high reconstruction accuracy. However, the traditional patch-match algorithm needs to iteratively calculate the optimal disparity d for each pixel of image in an orderly manner, which resulting in a high running time. In order to solve this problem, a learning-based model on the basis of traditional patch-match algorithm as a guide to reduce the running time and improve the accuracy of stereo reconstruction was introduced. First, the deep learning model was used to output the initial disparity map of each pixel with heteroscedastic uncertainty, which was used to measure the accuracy of the disparity predicted by the network model. Then, the heteroscedastic uncertainty and initial disparity were taken as the prior information of patch-match algorithm. Finally, in the plane refinement step, the heteroscedastic uncertainty of each pixel was used to dynamically adjust its search interval to achieve the goal of reducing the running time. On the Middlebury dataset, compared with the original algorithm, the running time of the improved algorithm is reduced by 20%, and the reconstruction accuracy of the discontinuous region is slightly improved.

    Tools

    Get Citation

    Copy Citation Text

    Lizheng SONG, Dongyun LIN, Xiafu PENG, Tengfei LIU. Patch-match binocular 3D reconstruction based on deep learning[J]. Journal of Applied Optics, 2022, 43(3): 436

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: OE INFORMATION ACQUISITION AND PROCESSING

    Received: Nov. 19, 2021

    Accepted: --

    Published Online: Jun. 7, 2022

    The Author Email:

    DOI:10.5768/JAO202243.0302003

    Topics