Corpus ID: 215828163

AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss

@article{Zhu2019AdaCoSegAS,
  title={AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss},
  author={Chenyang Zhu and Kai Xu and Siddhartha Chaudhuri and Li Yi and Leonidas J. Guibas and Hao Zhang},
  journal={arXiv: Computer Vision and Pattern Recognition},
  year={2019}
}
  • Chenyang Zhu, Kai Xu, +3 authors Hao Zhang
  • Published 2019
  • Computer Science
  • arXiv: Computer Vision and Pattern Recognition
  • We introduce AdaCoSeg, a deep neural network architecture for adaptive co-segmentation of a set of 3D shapes represented as point clouds. Differently from the familiar single-instance segmentation problem, co-segmentation is intrinsically contextual: how a shape is segmented can vary depending on the set it is in. Hence, our network features an adaptive learning module to produce a consistent shape segmentation which adapts to a set. Specifically, given an input set of unsegmented shapes, we… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    Unsupervised 3D shape segmentation and co-segmentation via deep learning

    VIEW 3 EXCERPTS

    3D Shape Segmentation with Projective Convolutional Networks

    VIEW 3 EXCERPTS

    BAE-NET: Branched Autoencoder for Shape Co-Segmentation

    VIEW 8 EXCERPTS

    Co-Segmentation of 3D Shapes via Subspace Clustering

    VIEW 2 EXCERPTS

    3D shape segmentation via shape fully convolutional networks

    VIEW 1 EXCERPT

    SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

    VIEW 2 EXCERPTS