Attention-based network for low-light image enhancement

Simple item page
dc.contributor.authorZhang, C.
dc.contributor.authorYan, Q.
dc.contributor.authorZhu, Y.
dc.contributor.authorLi, X.
dc.contributor.authorSun, J.
dc.contributor.authorZhang, Y.
dc.contributor.conferenceIEEE International Conference on Multimedia and Expo (ICME) (6 Jul 2020 - 10 Jul 2020 : virtual online)
dc.date.issued2020
dc.description.abstractThe captured images under low-light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task, but these methods often failed in an extreme low-light environment and amplified the underlying noise in the input image. To address such a difficult problem, this paper presents a novel attention-based neural network to generate high-quality enhanced low-light images from the raw sensor data. Specifically, we first employ attention strategy (i.e. spatial attention and channel attention modules) to suppress undesired chromatic aberration and noise. The spatial attention module focuses on denoising by taking advantage of the non-local correlation in the image. The channel attention module guides the network to refine redundant colour features. Furthermore, we propose a new pooling layer, called inverted shuffle layer, which adaptively selects useful information from previous features. Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.
dc.description.statementofresponsibilityCheng Zhang, Qingsen Yan, Yu Zhu, Xianjun Li, Jinqiu Sun, Yanning Zhang
dc.identifier.citationProceedings / IEEE International Conference on Multimedia and Expo. IEEE International Conference on Multimedia and Expo, 2020, vol.2020-July, pp.1-6
dc.identifier.doi10.1109/ICME46284.2020.9102774
dc.identifier.isbn9781728113319
dc.identifier.issn1945-7871
dc.identifier.issn1945-788X
dc.identifier.urihttps://hdl.handle.net/2440/132233
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeonline
dc.relation.granthttp://purl.org/au-research/grants/arc/DP160100703
dc.relation.ispartofseriesIEEE International Conference on Multimedia and Expo
dc.rights© 2020 IEEE.
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/9099125/proceeding
dc.subjectLow-Light Image Enhancement; Image Denoising; Attention Mechanism
dc.titleAttention-based network for low-light image enhancement
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications