Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, Yagiz Aksoy

CVPR 2021 pp. 9685-9694

doi:10.1109/CVPR46437.2021.00956 /cvpr/2021/miangoleh2021cvpr-boosting/

Abstract

Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method builds on our analysis on how the input resolution and the scene structure affects depth estimation performance. We demonstrate that there is a trade-off between a consistent scene structure and the high-frequency details, and merge low- and high-resolution estimations to take advantage of this duality using a simple depth merging network. We present a double estimation method that improves the whole-image depth estimation and a patch selection method that adds local details to the final result. We demonstrate that by merging estimations at different resolutions with changing context, we can generate multi-megapixel depth maps with a high level of detail using a pre-trained model.

PDF CVPR Semantic Scholar

Cite

Text

Miangoleh et al. "Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00956

Markdown

[Miangoleh et al. "Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/miangoleh2021cvpr-boosting/) doi:10.1109/CVPR46437.2021.00956

BibTeX

@inproceedings{miangoleh2021cvpr-boosting,
  title     = {{Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging}},
  author    = {Miangoleh, S. Mahdi H. and Dille, Sebastian and Mai, Long and Paris, Sylvain and Aksoy, Yagiz},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {9685-9694},
  doi       = {10.1109/CVPR46437.2021.00956},
  url       = {https://mlanthology.org/cvpr/2021/miangoleh2021cvpr-boosting/}
}