Local diffusion map signature for symmetry-aware non-rigid shape correspondence

Meng Wang, Yi Fang

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

    Abstract

    Identifying accurate correspondences information among different shapes is of great importance in shape analysis such as shape registration, segmentation and retrieval. This paper aims to develop a paradigm to address the challenging issues posed by shape structural variation and symmetry ambiguity. Specifically, the proposed research developed a novel shape signature based on local diffusion map on 3D surface, which is used to identify the shape correspondence through graph matching process. The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation determined by gradients of heat diffusion field. The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware. Experimental results on 3D shape correspondence demonstrate the superior performance of our proposed method over other state-of-the-art techniques in identifying correspondences for non-rigid shapes with symmetry ambiguity.

    Original languageEnglish (US)
    Title of host publicationMM 2016 - Proceedings of the 2016 ACM Multimedia Conference
    PublisherAssociation for Computing Machinery, Inc
    Pages526-530
    Number of pages5
    ISBN (Electronic)9781450336031
    DOIs
    StatePublished - Oct 1 2016
    Event24th ACM Multimedia Conference, MM 2016 - Amsterdam, United Kingdom
    Duration: Oct 15 2016Oct 19 2016

    Other

    Other24th ACM Multimedia Conference, MM 2016
    CountryUnited Kingdom
    CityAmsterdam
    Period10/15/1610/19/16

    Fingerprint

    Hot Temperature

    Keywords

    • 3D shape correspondence
    • 3D shape signature
    • Non-rigid shape matching

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Computer Vision and Pattern Recognition
    • Software

    Cite this

    Wang, M., & Fang, Y. (2016). Local diffusion map signature for symmetry-aware non-rigid shape correspondence. In MM 2016 - Proceedings of the 2016 ACM Multimedia Conference (pp. 526-530). Association for Computing Machinery, Inc. https://doi.org/10.1145/2964284.2967277

    Local diffusion map signature for symmetry-aware non-rigid shape correspondence. / Wang, Meng; Fang, Yi.

    MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2016. p. 526-530.

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

    Wang, M & Fang, Y 2016, Local diffusion map signature for symmetry-aware non-rigid shape correspondence. in MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, Inc, pp. 526-530, 24th ACM Multimedia Conference, MM 2016, Amsterdam, United Kingdom, 10/15/16. https://doi.org/10.1145/2964284.2967277
    Wang M, Fang Y. Local diffusion map signature for symmetry-aware non-rigid shape correspondence. In MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, Inc. 2016. p. 526-530 https://doi.org/10.1145/2964284.2967277
    Wang, Meng ; Fang, Yi. / Local diffusion map signature for symmetry-aware non-rigid shape correspondence. MM 2016 - Proceedings of the 2016 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2016. pp. 526-530
    @inproceedings{b9b8cc84bd4b4344ab36aebc680efc2e,
    title = "Local diffusion map signature for symmetry-aware non-rigid shape correspondence",
    abstract = "Identifying accurate correspondences information among different shapes is of great importance in shape analysis such as shape registration, segmentation and retrieval. This paper aims to develop a paradigm to address the challenging issues posed by shape structural variation and symmetry ambiguity. Specifically, the proposed research developed a novel shape signature based on local diffusion map on 3D surface, which is used to identify the shape correspondence through graph matching process. The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation determined by gradients of heat diffusion field. The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware. Experimental results on 3D shape correspondence demonstrate the superior performance of our proposed method over other state-of-the-art techniques in identifying correspondences for non-rigid shapes with symmetry ambiguity.",
    keywords = "3D shape correspondence, 3D shape signature, Non-rigid shape matching",
    author = "Meng Wang and Yi Fang",
    year = "2016",
    month = "10",
    day = "1",
    doi = "10.1145/2964284.2967277",
    language = "English (US)",
    pages = "526--530",
    booktitle = "MM 2016 - Proceedings of the 2016 ACM Multimedia Conference",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Local diffusion map signature for symmetry-aware non-rigid shape correspondence

    AU - Wang, Meng

    AU - Fang, Yi

    PY - 2016/10/1

    Y1 - 2016/10/1

    N2 - Identifying accurate correspondences information among different shapes is of great importance in shape analysis such as shape registration, segmentation and retrieval. This paper aims to develop a paradigm to address the challenging issues posed by shape structural variation and symmetry ambiguity. Specifically, the proposed research developed a novel shape signature based on local diffusion map on 3D surface, which is used to identify the shape correspondence through graph matching process. The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation determined by gradients of heat diffusion field. The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware. Experimental results on 3D shape correspondence demonstrate the superior performance of our proposed method over other state-of-the-art techniques in identifying correspondences for non-rigid shapes with symmetry ambiguity.

    AB - Identifying accurate correspondences information among different shapes is of great importance in shape analysis such as shape registration, segmentation and retrieval. This paper aims to develop a paradigm to address the challenging issues posed by shape structural variation and symmetry ambiguity. Specifically, the proposed research developed a novel shape signature based on local diffusion map on 3D surface, which is used to identify the shape correspondence through graph matching process. The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation determined by gradients of heat diffusion field. The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware. Experimental results on 3D shape correspondence demonstrate the superior performance of our proposed method over other state-of-the-art techniques in identifying correspondences for non-rigid shapes with symmetry ambiguity.

    KW - 3D shape correspondence

    KW - 3D shape signature

    KW - Non-rigid shape matching

    UR - http://www.scopus.com/inward/record.url?scp=84994644439&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84994644439&partnerID=8YFLogxK

    U2 - 10.1145/2964284.2967277

    DO - 10.1145/2964284.2967277

    M3 - Conference contribution

    SP - 526

    EP - 530

    BT - MM 2016 - Proceedings of the 2016 ACM Multimedia Conference

    PB - Association for Computing Machinery, Inc

    ER -