MURAL - Maynooth University Research Archive Library



    MouldingNet: Deep-Learning for 3D Object Reconstruction


    Burns, Tobias and Pearlmutter, Barak A. and McDonald, John (2019) MouldingNet: Deep-Learning for 3D Object Reconstruction. In: Irish Machine Vision & Image Processing Conference 2019, 28-30 August 2019, Technological University Dublin. (In Press)

    [img]
    Preview
    Download (1MB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    With the rise of deep neural networks a number of approaches for learning over 3D data have gained popularity. In this paper, we take advantage of one of these approaches, bilateral convolutional layers to propose a novel end-to-end deep auto-encoder architecture to efficiently encode and reconstruct 3D point clouds. Bilateral convolutional layers project the input point cloud onto an even tessellation of a hyperplane in the $(d+1)$-dimensional space known as the permutohedral lattice and perform convolutions over this representation. In contrast to existing point cloud based learning approaches, this allows us to learn over the underlying geometry of the object to create a robust global descriptor. We demonstrate its accuracy by evaluating across the shapenet and modelnet datasets, in order to illustrate 2 main scenarios, known and unknown object reconstruction. These experiments show that our network generalises well from seen classes to unseen classes.

    Item Type: Conference or Workshop Item (Poster)
    Keywords: MouldingNet; Deep-Learning; 3D Object Reconstruction; deep neural networks;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Item ID: 10988
    Depositing User: John McDonald
    Date Deposited: 23 Aug 2019 16:23
    Refereed: Yes
    Funders: Science Foundation Ireland, John & Pat Hume Scholarship
    URI:

      Repository Staff Only(login required)

      View Item Item control page

      Downloads

      Downloads per month over past year