Corpus ID: 219687587

3D Reconstruction of Novel Object Shapes from Single Images

@article{Thai20203DRO,
  title={3D Reconstruction of Novel Object Shapes from Single Images},
  author={Anh Thai and Stefan Stojanov and Vijay Upadhya and James M. Rehg},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.07752}
}
  • Anh Thai, Stefan Stojanov, +1 author James M. Rehg
  • Published 2020
  • Computer Science
  • ArXiv
  • The key challenge in single image 3D shape reconstruction is to ensure that deep models can generalize to shapes which were not part of the training set. This is difficult because the algorithm must infer the occluded portion of the surface by leveraging the shape characteristics of the training data, and can therefore be vulnerable to overfitting. Such generalization to unseen categories of objects is a function of architecture design and training approaches. This paper introduces SDFNet, a… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 47 REFERENCES
    3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
    • 653
    • PDF
    Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and Shading
    • 27
    • PDF
    3D ShapeNets: A deep representation for volumetric shapes
    • 1,833
    • PDF
    MarrNet : 3 D Shape Reconstruction via 2 . 5 D Sketches
    • 72
    • PDF
    Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
    • 307
    • PDF
    3D Object Reconstruction from a Single Depth View with Adversarial Learning
    • 95
    • PDF
    Learning Free-Form Deformations for 3D Object Reconstruction
    • 39
    • PDF
    DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
    • 56
    • Highly Influential
    • PDF
    Learning to Infer Implicit Surfaces without 3D Supervision
    • 28
    • PDF
    Occupancy Networks: Learning 3D Reconstruction in Function Space
    • 221
    • Highly Influential
    • PDF