Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction

Abstract

This paper proposes a novel single-image piecewise planar reconstruction technique that infers and enforces inter-plane relationships. Our approach takes a planar reconstruction result from an existing system, then utilizes convolutional neural network (CNN) to (1) classify if two planes are orthogonal or parallel; and 2) infer if two planes are touching and, if so, where in the image. We formulate an optimization problem to refine plane parameters and employ a message passing neural network to refine plane segmentation masks by enforcing the inter-plane relations. Our qualitative and quantitative evaluations demonstrate the effectiveness of the proposed approach in terms of plane parameters and segmentation accuracy.

Cite

Text

Qian and Furukawa. "Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58571-6_20

Markdown

[Qian and Furukawa. "Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/qian2020eccv-learning/) doi:10.1007/978-3-030-58571-6_20

BibTeX

@inproceedings{qian2020eccv-learning,
  title     = {{Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction}},
  author    = {Qian, Yiming and Furukawa, Yasutaka},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58571-6_20},
  url       = {https://mlanthology.org/eccv/2020/qian2020eccv-learning/}
}