Header

UZH-Logo

Maintenance Infos

Semi-dense 3D Reconstruction with a Stereo Event Camera


Zhou, Yi; Gallego, Guillermo; Rebecq, Henri; Kneip, Laurent; Li, Hongdong; Scaramuzza, Davide (2018). Semi-dense 3D Reconstruction with a Stereo Event Camera. In: Ferrari, Vittorio; Hebert, Martial; Sminchisescu, Cristian; Weiss, Yair. Computer Vision – ECCV 2018. Cham: Springer, 242-258.

Abstract

Event cameras are bio-inspired sensors that oer several advantages, such as low latency, high-speed and high dynamic range, to tackle challenging scenarios in computer vision. This paper presents a solution to the problem of 3D reconstruction from data captured by a stereo event-camera rig moving in a static scene, such as in the context of stereo Simultaneous Localization and Mapping. The proposed method consists of the optimization of an energy function designed to exploit small-baseline spatio-temporal consistency of events triggered across both stereo image planes. To improve the density of the reconstruction and to reduce the uncertainty of the estimation, a probabilistic depth-fusion strategy is also developed. The resulting method has no special requirements on either the motion of the stereo event-camera rig or on prior knowledge about the scene. Experiments demonstrate our method can deal with both texture-rich scenes as well as sparse scenes, outperforming state-of-the-art stereo methods based on event data image representations.

Abstract

Event cameras are bio-inspired sensors that oer several advantages, such as low latency, high-speed and high dynamic range, to tackle challenging scenarios in computer vision. This paper presents a solution to the problem of 3D reconstruction from data captured by a stereo event-camera rig moving in a static scene, such as in the context of stereo Simultaneous Localization and Mapping. The proposed method consists of the optimization of an energy function designed to exploit small-baseline spatio-temporal consistency of events triggered across both stereo image planes. To improve the density of the reconstruction and to reduce the uncertainty of the estimation, a probabilistic depth-fusion strategy is also developed. The resulting method has no special requirements on either the motion of the stereo event-camera rig or on prior knowledge about the scene. Experiments demonstrate our method can deal with both texture-rich scenes as well as sparse scenes, outperforming state-of-the-art stereo methods based on event data image representations.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

1 download since deposited on 30 Oct 2019
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Theoretical Computer Science
Physical Sciences > General Computer Science
Language:English
Date:2018
Deposited On:30 Oct 2019 15:23
Last Modified:25 May 2020 20:28
Publisher:Springer
Number:11205
ISBN:978-3-030-01245-8
Additional Information:978-3-030-01246-5 (E)
OA Status:Closed
Publisher DOI:https://doi.org/10.1007/978-3-030-01246-5_15
Other Identification Number:merlin-id:18691

Download

Closed Access: Download allowed only for UZH members

Content: Accepted Version
Filetype: PDF - Registered users only until 6 October 2020
Size: 1MB
View at publisher
Embargo till: 2020-10-06
Get full-text in a library