Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation

Christian Reinbacher, Gottfried Graber, Thomas Pock

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formulated on a per-event-basis, where we explicitly incorporate information about the asynchronous nature of events via an event manifold induced by the relative timestamps of events. In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.
Original languageEnglish
Publication statusE-pub ahead of print - 23 Sep 2016
EventBritish Machine Vision Conference - York, United Kingdom
Duration: 19 Sep 201622 Sep 2016

Conference

ConferenceBritish Machine Vision Conference
CountryUnited Kingdom
CityYork
Period19/09/1622/09/16

Fingerprint

Image reconstruction
Cameras
Pixels
Optical flows
Image quality
Experiments

Keywords

  • cs.CV

Cite this

Reinbacher, C., Graber, G., & Pock, T. (2016). Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation. Paper presented at British Machine Vision Conference, York, United Kingdom.

Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation. / Reinbacher, Christian; Graber, Gottfried; Pock, Thomas.

2016. Paper presented at British Machine Vision Conference, York, United Kingdom.

Research output: Contribution to conferencePaperResearchpeer-review

Reinbacher, C, Graber, G & Pock, T 2016, 'Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation' Paper presented at British Machine Vision Conference, York, United Kingdom, 19/09/16 - 22/09/16, .
Reinbacher C, Graber G, Pock T. Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation. 2016. Paper presented at British Machine Vision Conference, York, United Kingdom.
Reinbacher, Christian ; Graber, Gottfried ; Pock, Thomas. / Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation. Paper presented at British Machine Vision Conference, York, United Kingdom.
@conference{9414f40ed1a545f2943083bca54da439,
title = "Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation",
abstract = "Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formulated on a per-event-basis, where we explicitly incorporate information about the asynchronous nature of events via an event manifold induced by the relative timestamps of events. In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.",
keywords = "cs.CV",
author = "Christian Reinbacher and Gottfried Graber and Thomas Pock",
note = "Accepted to BMVC 2016 as oral presentation, 12 pages; British Machine Vision Conference ; Conference date: 19-09-2016 Through 22-09-2016",
year = "2016",
month = "9",
day = "23",
language = "English",

}

TY - CONF

T1 - Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation

AU - Reinbacher, Christian

AU - Graber, Gottfried

AU - Pock, Thomas

N1 - Accepted to BMVC 2016 as oral presentation, 12 pages

PY - 2016/9/23

Y1 - 2016/9/23

N2 - Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formulated on a per-event-basis, where we explicitly incorporate information about the asynchronous nature of events via an event manifold induced by the relative timestamps of events. In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.

AB - Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formulated on a per-event-basis, where we explicitly incorporate information about the asynchronous nature of events via an event manifold induced by the relative timestamps of events. In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.

KW - cs.CV

M3 - Paper

ER -