Multi-view 3D model reconstruction: Exploitation of color homogeneity in voxel mask

S. S. Wong, K. L. Chan

    Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

    2 Citations (Scopus)

    Abstract

    This project aims to reconstruct a 3D object model from an image sequence captured by a mobile camera. "Shape-from-Silhouette/Photo-consistency" approach is adopted for the volumetric model reconstruction. To correct the concavity error, a novel voxel mask in 3D space for measuring the color dispersion, instead of using the conventional block matching technique, is proposed to locate the concavity of the object surface. In addition, a new technique for partial surface estimation is implemented to overcome the reconstruction problem due to insufficient texture information or color homogeneity. Finally, a single texture map, which is generated from the original multi-view images, is rendered to the surface model. © 2004 IEEE.
    Original languageEnglish
    Title of host publicationProceedings - Third International Conference on Image and Graphics
    Pages142-145
    Publication statusPublished - 2004
    EventProceedings - Third International Conference on Image and Graphics - Hong Kong, Hong Kong
    Duration: 18 Dec 200420 Dec 2004

    Conference

    ConferenceProceedings - Third International Conference on Image and Graphics
    Country/TerritoryHong Kong
    CityHong Kong
    Period18/12/0420/12/04

    Research Keywords

    • Model reconstruction
    • Texture mapping

    Fingerprint

    Dive into the research topics of 'Multi-view 3D model reconstruction: Exploitation of color homogeneity in voxel mask'. Together they form a unique fingerprint.

    Cite this