Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

  title={Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry},
  author={Yifan Xu and T. Fan and Yi Yuan and Gurprit Singh},
  • Yifan Xu, T. Fan, +1 author Gurprit Singh
  • Published 2020
  • Computer Science, Physics
  • ArXiv
  • Deep implicit field regression methods are effective for 3D reconstruction from single-view images. However, the impact of different sampling patterns on the reconstruction quality is not well-understood. In this work, we first study the effect of point set discrepancy on the network training. Based on Farthest Point Sampling algorithm, we propose a sampling scheme that theoretically encourages better generalization performance, and results in fast convergence for SGD-based optimization… CONTINUE READING
    3 Citations
    Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations
    • PDF
    Dynamic Plane Convolutional Occupancy Networks
    • PDF


    DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
    • 92
    • Highly Influential
    • PDF
    A Point Set Generation Network for 3D Object Reconstruction from a Single Image
    • Haoqiang Fan, H. Su, L. Guibas
    • Computer Science, Mathematics
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 727
    • PDF
    3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
    • 733
    • PDF
    Efficient Dense Point Cloud Object Reconstruction Using Deformation Vector Fields
    • 18
    • PDF
    Occupancy Networks: Learning 3D Reconstruction in Function Space
    • 324
    • Highly Influential
    • PDF
    Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
    • 136
    • PDF
    Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
    • 158
    • PDF
    Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
    • 7
    • PDF
    Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images
    • 35
    • PDF
    Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
    • 380
    • PDF