Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow

Federico Paredes-Vallés*, Kirk Y.W. Scheper, Christope De Wagter, Guido C.H.E. De Croon

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Event cameras have recently gained significant traction since they open up new avenues for low-latency and low-power solutions to complex computer vision problems. To unlock these solutions, it is necessary to develop algorithms that can leverage the unique nature of event data. However, the current state-of-the-art is still highly influenced by the frame-based literature, and usually fails to deliver on these promises. In this work, we take this into consideration and propose a novel self-supervised learning pipeline for the sequential estimation of event-based optical flow that allows for the scaling of the models to high inference frequencies. At its core, we have a continuously-running stateful neural model that is trained using a novel formulation of contrast maximization that makes it robust to nonlinearities and varying statistics in the input events. Results across multiple datasets confirm the effectiveness of our method, which establishes a new state of the art in terms of accuracy for approaches trained or optimized without ground truth.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PublisherIEEE
Pages9661-9671
Number of pages11
ISBN (Electronic)9798350307184
DOIs
Publication statusPublished - 2023
Event2023 IEEE/CVF International Conference on Computer Vision - Paris, France
Duration: 2 Oct 20236 Oct 2023

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499

Conference

Conference2023 IEEE/CVF International Conference on Computer Vision
Abbreviated titleICCV 2023
Country/TerritoryFrance
CityParis
Period2/10/236/10/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Fingerprint

Dive into the research topics of 'Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow'. Together they form a unique fingerprint.

Cite this