papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-04-03
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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.02028

PDF

https://arxiv.org/pdf/1904.02028


Similar Posts

Comments