Laser & Optoelectronics Progress, Volume. 62, Issue 4, 0411002(2025)

Three-Dimensional Reconstruction Method Based on Multiscale S-Density Strategy

Xunsheng Ji*, Yin Zhu, and Jielong Yang
Author Affiliations
  • College of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu , China
  • show less

    Multiview three-dimensional (3D) reconstruction technology, which is an important driving technology in fields such as medical imaging and cultural relic protection, is gaining increasing attention and research interest. Despite recent successes in 3D reconstruction methods using implicit neural representations, challenges remain in terms of accurately capturing object details and processing complex scenes. To address these issues, a 3D reconstruction method based on a multiscale S-density strategy, called MS-Neus, is proposed. The proposed method attempts to improve the reconstruction quality and fidelity by obtaining more local information and expanding the expressiveness of implicit neural representations. The integration of information across different scales results in accurate and detailed reconstruction outcomes, showcasing rich details and realism in complex scenes. The experimental results obtained on the DTU MVS dataset demonstrate that the proposed method outperforms existing techniques for high-quality surface reconstruction, more accurately reproducing geometric shapes and detailed object features, particularly excelling in the management of complex geometric structures.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Xunsheng Ji, Yin Zhu, Jielong Yang. Three-Dimensional Reconstruction Method Based on Multiscale S-Density Strategy[J]. Laser & Optoelectronics Progress, 2025, 62(4): 0411002

    Download Citation

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

    Category: Imaging Systems

    Received: May. 27, 2024

    Accepted: Jun. 27, 2024

    Published Online: Feb. 10, 2025

    The Author Email:

    DOI:10.3788/LOP241372

    CSTR:32186.14.LOP241372

    Topics