Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation

Matan Goldman
Matan Goldman

CVPR Workshops, pp. 0-0, 2019.

Cited by: 5|Bibtex|Views16
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

The field of self-supervised monocular depth estimation has seen huge advancements in recent years. Most methods assume stereo data is available during training but usually under-utilize it and only treat it as a reference signal. We propose a novel self-supervised approach which uses both left and right images equally during training, bu...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments