3DContextNet: K-D Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues

ECCVW 2018 pp. 314-330

doi:10.1007/978-3-030-11015-4_24 /eccvw/2018/zeng2018eccvw-3dcontextnet/

Abstract

Classification and segmentation of 3D point clouds are important tasks in computer vision. Because of the irregular nature of point clouds, most of the existing methods convert point clouds into regular 3D voxel grids before they are used as input for ConvNets. Unfortunately, voxel representations are highly insensitive to the geometrical nature of 3D data. More recent methods encode point clouds to higher dimensional features to cover the global 3D space. However, these models are not able to sufficiently capture the local structures of point clouds.

PDF ECCVW Semantic Scholar

Cite

Text

Zeng and Gevers. "3DContextNet: K-D Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11015-4_24

Markdown

[Zeng and Gevers. "3DContextNet: K-D Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/zeng2018eccvw-3dcontextnet/) doi:10.1007/978-3-030-11015-4_24

BibTeX

@inproceedings{zeng2018eccvw-3dcontextnet,
  title     = {{3DContextNet: K-D Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues}},
  author    = {Zeng, Wei and Gevers, Theo},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {314-330},
  doi       = {10.1007/978-3-030-11015-4_24},
  url       = {https://mlanthology.org/eccvw/2018/zeng2018eccvw-3dcontextnet/}
}