Event Collapse in Contrast Maximization Frameworks

dc.contributor.authorShiba, Shintaro
dc.contributor.authorAoki, Yoshimitsu
dc.contributor.authorGallego, Guillermo
dc.date.accessioned2022-08-10T09:18:02Z
dc.date.available2022-08-10T09:18:02Z
dc.date.issued2022-07-11
dc.date.updated2022-08-03T16:27:48Z
dc.description.abstractContrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space–time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models.en
dc.identifier.eissn1424-8220
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/17328
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-16109
dc.language.isoenen
dc.rightsLicensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddc620 Ingenieurwissenschaften und zugeordnete Tätigkeitende
dc.subject.othercomputer visionen
dc.subject.otherintelligent sensorsen
dc.subject.otherroboticsen
dc.subject.otherevent-based cameraen
dc.subject.othercontrast maximizationen
dc.subject.otheroptical flowen
dc.subject.othermotion estimationen
dc.titleEvent Collapse in Contrast Maximization Frameworksen
dc.typeArticleen
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.articlenumber5190en
dcterms.bibliographicCitation.doi10.3390/s22145190en
dcterms.bibliographicCitation.issue14en
dcterms.bibliographicCitation.journaltitleSensorsen
dcterms.bibliographicCitation.originalpublishernameMDPIen
dcterms.bibliographicCitation.originalpublisherplaceBaselen
dcterms.bibliographicCitation.volume22en
tub.accessrights.dnbfreeen
tub.affiliationFak. 4 Elektrotechnik und Informatik>Inst. Technische Informatik und Mikroelektronik>FG Robotic Interactive Perceptionde
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Robotic Interactive Perceptionde
tub.affiliation.instituteInst. Technische Informatik und Mikroelektronikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
Files
Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
sensors-22-05190-v3.pdf
Size:
5.09 MB
Format:
Adobe Portable Document Format
Description:
Collections