Learning Shape Templates With Structured Implicit Functions

@article{Genova2019LearningST,
  title={Learning Shape Templates With Structured Implicit Functions},
  author={Kyle Genova and F. Cole and D. Vlasic and Aaron Sarna and W. Freeman and T. Funkhouser},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={7153-7163}
}
  • Kyle Genova, F. Cole, +3 authors T. Funkhouser
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes, previous methods generally use a library of hand-made templates. In this paper, we investigate learning a general shape template from data. To allow for widely varying geometry and topology, we choose an implicit surface representation based on composition of… CONTINUE READING
    73 Citations
    Deep Parametric Shape Predictions Using Distance Fields
    • 11
    • PDF
    Deep Implicit Templates for 3D Shape Representation
    • 1
    • Highly Influenced
    • PDF
    Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
    • 1
    • PDF
    Learning Generative Models of Shape Handles
    • 1
    • PDF
    Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
    • Highly Influenced
    • PDF
    Local Implicit Grid Representations for 3D Scenes
    • 41
    • PDF
    Local Deep Implicit Functions for 3D Shape
    • 29
    • PDF
    Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
    • 1
    • PDF
    Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
    • 34
    • PDF

    References

    SHOWING 1-10 OF 71 REFERENCES
    Parsing Geometry Using Structure-Aware Shape Templates
    • 13
    • PDF
    3D ShapeNets: A deep representation for volumetric shapes
    • 2,121
    • PDF
    Learning part-based templates from large collections of 3D shapes
    • 185
    • PDF
    Learning Implicit Fields for Generative Shape Modeling
    • Zhiqin Chen, Hao Zhang
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 236
    • PDF
    Exploration of continuous variability in collections of 3D shapes
    • 45
    Learning Shape Abstractions by Assembling Volumetric Primitives
    • 146
    • Highly Influential
    • PDF
    Multi-view Convolutional Neural Networks for 3D Shape Recognition
    • 1,468
    • PDF
    Learning Category-Specific Mesh Reconstruction from Image Collections
    • 209
    • PDF
    DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
    • 374
    • PDF
    3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks
    • 86
    • PDF