Modeling 2D Appearance Evolution for 3D Object Categorization

Hasan F.M. Zaki, Faisal Shafait, Ajmal Mian

    Research output: Chapter in Book/Conference paperConference paper

    2 Citations (Scopus)

    Abstract

    3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB and depth images from multiple viewpoints on a uniform sphere. Using rank pooling, we propose two methods to learn the appearance evolution of the 2D views. Firstly, we train view-invariant models based on a deep convolutional neural network (CNN) using the rendered RGB-D images and learn to rank the first fully connected layer activations and, therefore, capture the evolution of these extracted features. The parameters learned during this process are used as the 3D shape representations. In the second method, we learn the aggregation of the views from the outset by employing the ranking machine to the rendered RGB- D images directly, which produces aggregated 2D images which we term as ''3D shape images". We then learn CNN models on this novel shape representation for both RGB and depth which encode salient geometrical structure of the polygon. Experiments on the ModelNet40 and ModelNet10 datasets show that the proposed method consistently outperforms existing state-of-the-art algorithms in 3D shape recognition.

    Original languageEnglish
    Title of host publication2016 International Conference on Digital Image Computing: Techniques and Applications
    EditorsM Blumenstein, B Lovell , C Fookes , Z Wang, Y Gao, J Zhou , A.W Liew
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    ISBN (Electronic)9781509028962
    DOIs
    Publication statusPublished - 22 Dec 2016
    Event2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016: DICTA 2016 - Gold Coast, Australia
    Duration: 30 Nov 20162 Dec 2016

    Conference

    Conference2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016
    CountryAustralia
    CityGold Coast
    Period30/11/162/12/16

    Fingerprint Dive into the research topics of 'Modeling 2D Appearance Evolution for 3D Object Categorization'. Together they form a unique fingerprint.

  • Cite this

    Zaki, H. F. M., Shafait, F., & Mian, A. (2016). Modeling 2D Appearance Evolution for 3D Object Categorization. In M. Blumenstein, B. Lovell , C. Fookes , Z. Wang, Y. Gao, J. Zhou , & A. W. Liew (Eds.), 2016 International Conference on Digital Image Computing: Techniques and Applications IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2016.7797065