DC Field | Value | Language |
---|---|---|
dc.contributor.author | LEE, SOHYUN | - |
dc.contributor.author | RIM, JAESUNG | - |
dc.contributor.author | JEONG, BOSEUNG | - |
dc.contributor.author | KIM, GEONU | - |
dc.contributor.author | WOO, BYUNGJU | - |
dc.contributor.author | LEE, HAECHAN | - |
dc.contributor.author | CHO, SUNGHYUN | - |
dc.contributor.author | KWAK, SUHA | - |
dc.date.accessioned | 2023-12-18T05:02:04Z | - |
dc.date.available | 2023-12-18T05:02:04Z | - |
dc.date.created | 2023-12-16 | - |
dc.date.issued | 2023-06-20 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/119559 | - |
dc.description.abstract | We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality significantly. To address the first issue, we develop a ded-icated camera system and build a new dataset of real low-light images with accurate pose labels. Thanks to our camera system, each low-light image in our dataset is coupled with an aligned well-lit image, which enables accurate pose labeling and is used as privileged information during training. We also propose a new model and a new training strategy that fully exploit the privileged information to learn representation insensitive to lighting conditions. Our method demonstrates outstanding performance on real extremely low-light images, and extensive analyses validate that both of our model and dataset contribute to the success. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.relation.isPartOf | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.relation.isPartOf | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Human Pose Estimation in Extremely Low-Light Conditions | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp.704 - 714 | - |
dc.citation.conferenceDate | 2023-06-18 | - |
dc.citation.conferencePlace | CA | - |
dc.citation.endPage | 714 | - |
dc.citation.startPage | 704 | - |
dc.citation.title | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.contributor.affiliatedAuthor | LEE, SOHYUN | - |
dc.contributor.affiliatedAuthor | RIM, JAESUNG | - |
dc.contributor.affiliatedAuthor | JEONG, BOSEUNG | - |
dc.contributor.affiliatedAuthor | KIM, GEONU | - |
dc.contributor.affiliatedAuthor | LEE, HAECHAN | - |
dc.contributor.affiliatedAuthor | CHO, SUNGHYUN | - |
dc.contributor.affiliatedAuthor | KWAK, SUHA | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.