Header

UZH-Logo

Maintenance Infos

EMVS: Event-Based Multi-View Stereo - 3D Reconstruction with an Event Camera in Real-Time


Rebecq, Henri; Gallego Bonet, Guillermo; Müggler, Elias; Scaramuzza, Davide (2017). EMVS: Event-Based Multi-View Stereo - 3D Reconstruction with an Event Camera in Real-Time. International Journal of Computer Vision:Epub ahead of print.

Abstract

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the order of microseconds. However, because the output is composed of a sequence of asynchronous events rather than actual intensity images, traditional vision algorithms cannot be applied, so that a paradigm shift is needed. We introduce the problem of event-based multi-view stereo (EMVS) for event cameras and propose a solution to it. Unlike traditional MVS methods, which address the problem of estimating dense 3D structure from a set of known viewpoints, EMVS estimates semi-dense 3D structure from an event camera with known trajectory. Our EMVS solution elegantly exploits two inherent properties of an event camera: (1) its ability to respond to scene edges—which naturally provide semi-dense geometric information without any pre-processing operation—and (2) the fact that it provides continuous measurements as the sensor moves. Despite its simplicity (it can be implemented in a few lines of code), our algorithm is able to produce accurate, semi-dense depth maps, without requiring any explicit data association or intensity estimation. We successfully validate our method on both synthetic and real data. Our method is computationally very efficient and runs in real-time on a CPU.

Abstract

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the order of microseconds. However, because the output is composed of a sequence of asynchronous events rather than actual intensity images, traditional vision algorithms cannot be applied, so that a paradigm shift is needed. We introduce the problem of event-based multi-view stereo (EMVS) for event cameras and propose a solution to it. Unlike traditional MVS methods, which address the problem of estimating dense 3D structure from a set of known viewpoints, EMVS estimates semi-dense 3D structure from an event camera with known trajectory. Our EMVS solution elegantly exploits two inherent properties of an event camera: (1) its ability to respond to scene edges—which naturally provide semi-dense geometric information without any pre-processing operation—and (2) the fact that it provides continuous measurements as the sensor moves. Despite its simplicity (it can be implemented in a few lines of code), our algorithm is able to produce accurate, semi-dense depth maps, without requiring any explicit data association or intensity estimation. We successfully validate our method on both synthetic and real data. Our method is computationally very efficient and runs in real-time on a CPU.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

2 downloads since deposited on 21 Mar 2018
2 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Date:7 November 2017
Deposited On:21 Mar 2018 15:36
Last Modified:13 Apr 2018 11:43
Publisher:Springer
ISSN:0920-5691
OA Status:Green
Publisher DOI:https://doi.org/10.1007/s11263-017-1050-6
Official URL:http://rpg.ifi.uzh.ch/docs/IJCV17_Rebecq.pdf
Other Identification Number:merlin-id:16262

Download

Download PDF  'EMVS: Event-Based Multi-View Stereo - 3D Reconstruction with an Event Camera in Real-Time'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 32MB
View at publisher
Embargo till: 2018-11-01