CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

Jose M. Facil1
Benjamin Ummenhofer2,3
Huizhong Zhou2
Luis Montesano1,4
Thomas Brox*2
Javier Civera*1
* Equal Contribution
1 University of Zaragoza 2 University of Freiburg 3 Intel Labs 4 Bitbrain


Accepted for Poster Presentation at CVPR 2019
[ArXiv]
[Paper+Supp]
[Code]



Abstract

Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.



Code




Paper and Bibtex

[ArXiv]

Citation
 
Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou,
Luis Montesano, Thomas Brox and Javier Civera
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[Bibtex]
@inproceedings{facil2019camconvs,
    author = {Facil, Jose M. and Ummenhofer, Benjamin and Zhou, Huizhong and
    Montesano, Luis and Brox, Thomas and Civera, Javier},
    title = {{CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth}},
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2019},
    url = "https://webdiis.unizar.es/~jmfacil/camconvs/"
}


Acknowledgements

This project was in part funded by the Spanish government (DPI2015-67275), the EU Horizon 2020 project Trimbot2020, the Aragón government (DGA-T45\_17R/FSE) and Fundación CAI-Ibercaja. We also thank Facebook for their P100 server donation and gift funding; and Nvidia for their Titan X and Xp donation.