Monocular Depth Estimation Using Relative Depth Maps

Lee, Jae-Han; Kim, Chang-Su

doi:10.1109/CVPR.2019.00996

Monocular Depth Estimation Using Relative Depth Maps

Jae-Han Lee, Chang-Su Kim

CVPR 2019

doi:10.1109/CVPR.2019.00996 /cvpr/2019/lee2019cvpr-monocular/

Abstract

We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.

PDF CVPR Semantic Scholar

Cite

Text

Lee and Kim. "Monocular Depth Estimation Using Relative Depth Maps." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00996

Markdown

[Lee and Kim. "Monocular Depth Estimation Using Relative Depth Maps." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/lee2019cvpr-monocular/) doi:10.1109/CVPR.2019.00996

BibTeX

@inproceedings{lee2019cvpr-monocular,
  title     = {{Monocular Depth Estimation Using Relative Depth Maps}},
  author    = {Lee, Jae-Han and Kim, Chang-Su},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2019},
  doi       = {10.1109/CVPR.2019.00996},
  url       = {https://mlanthology.org/cvpr/2019/lee2019cvpr-monocular/}
}