Learning to Super Resolve Intensity Images from Events

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 179
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorMostafavi, Mohammadko
dc.contributor.authorChoi, Jonghyunko
dc.contributor.authorYoon, Kuk-Jinko
dc.date.accessioned2020-03-25T02:20:26Z-
dc.date.available2020-03-25T02:20:26Z-
dc.date.created2020-02-26-
dc.date.created2020-02-26-
dc.date.issued2020-06-16-
dc.identifier.citationIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)-
dc.identifier.urihttp://hdl.handle.net/10203/273487-
dc.description.abstractAn event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic sensing range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an end-to-end network to reconstruct high resolution, high dynamic range (HDR) images from the event streams. The reconstructed images using the proposed method is in better quality than the combination of state-ofthe-art intensity image reconstruction algorithms and the state-of-the-art super resolution schemes. We further evaluate our algorithm on multiple real-world sequences showing the ability to generate high quality images in the zeroshot cross dataset transfer setting.-
dc.languageEnglish-
dc.publisherIEEE/CVF-
dc.titleLearning to Super Resolve Intensity Images from Events-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationnameIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)-
dc.identifier.conferencecountryUS-
dc.contributor.localauthorYoon, Kuk-Jin-
dc.contributor.nonIdAuthorMostafavi, Mohammad-
dc.contributor.nonIdAuthorChoi, Jonghyun-
Appears in Collection
ME-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0