ML Anthology

Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction

Fuyang Zhang, Nelson Nauata, Yasutaka Furukawa
CVPR 2020
doi:10.1109/CVPR42600.2020.00287 /cvpr/2020/zhang2020cvpr-convmpn/

Abstract

This paper proposes a novel message passing neural (MPN) architecture Conv-MPN, which reconstructs an outdoor building as a planar graph from a single RGB image. Conv-MPN is specifically designed for cases where nodes of a graph have explicit spatial embedding. In our problem, nodes correspond to building edges in an image. Conv-MPN is different from MPN in that 1) the feature associated with a node is represented as a feature volume instead of a 1D vector; and 2) convolutions encode messages instead of fully connected layers. Conv-MPN learns to select a true subset of nodes (i.e., building edges) to reconstruct a building planar graph. Our qualitative and quantitative evaluations over 2,000 buildings show that Conv-MPN makes significant improvements over the existing fully neural solutions. We believe that the paper has a potential to open a new line of graph neural network research for structured geometry reconstruction.

PDF CVPR Semantic Scholar

Cite

Text

Zhang et al. "Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00287

Markdown

[Zhang et al. "Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/zhang2020cvpr-convmpn/) doi:10.1109/CVPR42600.2020.00287

BibTeX

@inproceedings{zhang2020cvpr-convmpn,
  title     = {{Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction}},
  author    = {Zhang, Fuyang and Nauata, Nelson and Furukawa, Yasutaka},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00287},
  url       = {https://mlanthology.org/cvpr/2020/zhang2020cvpr-convmpn/}
}