Full metadata record

DC Field Value Language
dc.contributor.authorJung, Hyungjoo-
dc.contributor.authorSohn, Kwanghoon-
dc.contributor.authorHa, Namkoo-
dc.contributor.authorJang, Hyunsung-
dc.date.accessioned2024-01-19T09:08:38Z-
dc.date.available2024-01-19T09:08:38Z-
dc.date.created2022-02-26-
dc.date.issued2021-02-
dc.identifier.issn2159-5399-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/113578-
dc.description.abstractWe present a new deep learning framework for low-contrast image enhancement, which trains the network using the multi-exposure sequences rather than explicit ground-truth images. The purpose of our method is to enhance a low-contrast image so as to contain abundant details in various exposure levels. To realize this, we propose to design the loss function using the structure tensor representation, which has been widely used as high-dimensional image contrast. Our loss function penalizes the difference of the structure tensors between the network output and the multi-exposure images in a multi-scale manner. Eventually, the network trained by the loss function produces a high-quality image approximating the overall contrast of the sequence. We provide in-depth analysis on our method and comparison with conventional loss functions. Quantitative and qualitative evaluations demonstrate that the proposed method outperforms the existing state-of-the art approaches in various benchmarks.-
dc.languageEnglish-
dc.publisherASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE-
dc.titleDeep Low-Contrast Image Enhancement using Structure Tensor Representation-
dc.typeConference-
dc.description.journalClass1-
dc.identifier.bibliographicCitation35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence, pp.1725 - 1733-
dc.citation.title35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence-
dc.citation.startPage1725-
dc.citation.endPage1733-
dc.citation.conferencePlaceUS-
dc.citation.conferencePlaceELECTR NETWORK-
dc.citation.conferenceDate2021-02-02-
dc.relation.isPartOfTHIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE-
dc.identifier.wosid000680423501091-
Appears in Collections:
KIST Conference Paper > 2021
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE