Corpus ID: 214795329

Deformation-Aware 3D Model Embedding and Retrieval

@article{Uy2020DeformationAware3M,
  title={Deformation-Aware 3D Model Embedding and Retrieval},
  author={Mikaela Angelina Uy and Jingwei Huang and Minhyuk Sung and Tolga Birdal and L. Guibas},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.01228}
}
  • Mikaela Angelina Uy, Jingwei Huang, +2 authors L. Guibas
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • We introduce a new problem of $\textit{retrieving}$ 3D models that are not just similar but are deformable to a given query shape. We then present a novel deep $\textit{deformation-aware}$ embedding to solve this retrieval task. 3D model retrieval is a fundamental operation for recovering a clean and complete 3D model from a noisy and partial 3D scan. However, given a finite collection of 3D shapes, even the closest model to a query may not be a satisfactory reconstruction. This motivates us to… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    MeshODE: A Robust and Scalable Framework for Mesh Deformation
    ShapeFlow: Learnable Deformations Among 3D Shapes

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 65 REFERENCES
    Relay node placement in large scale wireless sensor networks
    343
    National survey of mycobacterial diseases other than tuberculosis in Korea
    • 1995
    Laplacian Forests: Semantic Image Segmentation by Guided Bagging
    27
    Quasi-Periodicity in Islamic Geometric Design
    8
    Regression testing minimization, selection and prioritization: a survey
    966