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

Jose M. Facil; Benjamin Ummenhofer; Huizhong Zhou; Luis Montesano; Thomas Brox; Javier Civera

CVPR 2019poster173 citations

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

Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera

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.

BibTeX

@inproceedings{cvpr2019_camconvscameraaw,
  title = {CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth},
  author = {Jose M. Facil and Benjamin Ummenhofer and Huizhong Zhou and Luis Montesano and Thomas Brox and Javier Civera},
  booktitle = {CVPR 2019},
  year = {2019}
}