Improving deep monocular depth predictions using dense narrow field of view depth images

Improving deep monocular depth predictions using dense narrow field of view depth images

In this work we study a depth prediction problem where we provide a narrow field of view depth image and a wide field of view RGB image to a deep network tasked with predicting the depth for the entire RGB image. We show that by providing a narrow field of view depth image, we improve results for th...

Full description

Bibliographic Details
Main Author: Möckelind, Christoffer
Format: Others
Language:English
Published: KTH, Robotik, perception och lärande, RPL 2018
Subjects:
Deep learning
Monocular
Depth estimation
Narrow field of view
RGB
RGBD
Noicy depth
Dense depth
Narrow depth
Sparse depth
Computer Sciences
Datavetenskap (datalogi)
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-235660

Similar Items