SDFConnect: Neural Implicit Surface Reconstruction of a Sparse Point Cloud with Topological Constraints

Anushrut Jignasu, Aditya Balu, Soumik Sarkar, Chinmay Hegde, Baskar Ganapathysubramanian, Adarsh Krishnamurthy

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present a novel approach for neural implicit surface reconstruction from relatively sparse point cloud to ensure the reconstruction of a single connected component. We introduce a topological loss term based on persistent homology to reconstruct a manifold object of genus 1. Building on the Neural Pull [25] framework, our method demonstrates superior performance in preserving the integrity of complex 3D geometries, evident through both visual and empirical comparisons. Our contributions include the integration of persistent diagrams to refine shape topology and a topological loss term to constrain existing reconstruction pipelines to a single connected component. This advancement allows for the seamless integration of topological data analysis with implicit surface reconstruction.

    Original languageEnglish (US)
    Title of host publicationProceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
    PublisherIEEE Computer Society
    Pages5271-5279
    Number of pages9
    ISBN (Electronic)9798350365474
    DOIs
    StatePublished - 2024
    Event2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 - Seattle, United States
    Duration: Jun 16 2024Jun 22 2024

    Publication series

    NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
    ISSN (Print)2160-7508
    ISSN (Electronic)2160-7516

    Conference

    Conference2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
    Country/TerritoryUnited States
    CitySeattle
    Period6/16/246/22/24

    Keywords

    • persistent homology
    • signed distance fields
    • surface reconstruction
    • topological data analysis

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'SDFConnect: Neural Implicit Surface Reconstruction of a Sparse Point Cloud with Topological Constraints'. Together they form a unique fingerprint.

    Cite this