Header

UZH-Logo

Maintenance Infos

REMODE: probabilistic, monocular dense reconstruction in real time


Pizzoli, Matia; Forster, Christian; Scaramuzza, Davide (2014). REMODE: probabilistic, monocular dense reconstruction in real time. In: IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May 2014 - 7 June 2014, 2609-2616.

Abstract

In this paper, we solve the problem of estimating dense and accurate depth maps from a single moving camera. A probabilistic depth measurement is carried out in real time on a per-pixel basis and the computed uncertainty is used to reject erroneous estimations and provide live feedback on the reconstruction progress. Our contribution is a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing. We demonstrate that our method outperforms state-of-the-art techniques in terms of accuracy, while exhibiting high efficiency in memory usage and computing power. We call our approach REMODE (REgularized MOnocular Depth Estimation). Our CUDA-based implementation runs at 30Hz on a laptop computer and is released as open-source software.

Abstract

In this paper, we solve the problem of estimating dense and accurate depth maps from a single moving camera. A probabilistic depth measurement is carried out in real time on a per-pixel basis and the computed uncertainty is used to reject erroneous estimations and provide live feedback on the reconstruction progress. Our contribution is a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing. We demonstrate that our method outperforms state-of-the-art techniques in terms of accuracy, while exhibiting high efficiency in memory usage and computing power. We call our approach REMODE (REgularized MOnocular Depth Estimation). Our CUDA-based implementation runs at 30Hz on a laptop computer and is released as open-source software.

Statistics

Citations

21 citations in Web of Science®
52 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

46 downloads since deposited on 12 Aug 2016
43 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:7 June 2014
Deposited On:12 Aug 2016 08:19
Last Modified:24 Sep 2017 05:11
Publisher:Institute of Electrical and Electronics Engineers
Series Name:IEEE International Conference on Robotics and Automation. Proceedings
ISSN:1050-4729
Publisher DOI:https://doi.org/10.1109/ICRA.2014.6907233
Related URLs:http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6907233 (Publisher)
http://www.icra2014.com/ (Organisation)
Other Identification Number:merlin-id:10214

Download

Preview Icon on Download
Preview
Content: Accepted Version
Filetype: PDF
Size: 3MB
View at publisher