HMM-based surface reconstruction from single images

Takayuki Nagai, Tadashi Naruse, Masaaki Ikehara, Akira Kurematsu

    Research output: Contribution to conferencePaperpeer-review

    31 Citations (Scopus)


    In this paper, a novel method of the surface reconstruction from a single monocular image is proposed. Our proposed approach (called shape from knowledge) is based on the knowledge of objects, which is acquired by learning from a number of samples. To achieve this, we investigate making use of the Hidden Markov Model (HMM) framework, which models the correspondence between an intensity image and its depth information. We have applied our algorithm to the 3-D face and 3-D hand reconstruction from single images, and the results show the effectiveness of the proposed method.

    Original languageEnglish
    Publication statusPublished - 2002 Jan 1
    EventInternational Conference on Image Processing (ICIP'02) - Rochester, NY, United States
    Duration: 2002 Sep 222002 Sep 25


    OtherInternational Conference on Image Processing (ICIP'02)
    Country/TerritoryUnited States
    CityRochester, NY

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Computer Vision and Pattern Recognition
    • Electrical and Electronic Engineering


    Dive into the research topics of 'HMM-based surface reconstruction from single images'. Together they form a unique fingerprint.

    Cite this