Zobrazeno 51 - 60
of 458
pro vyhledávání: '"Kyoung Mu Lee"'
Autor:
Sanghyun Son, Kyoung Mu Lee
Publikováno v:
Computer Vision ISBN: 9783030032432
Computer Vision
Computer Vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4924cd82051b3209cf6d8e46136f18cf
https://doi.org/10.1007/978-3-030-63416-2_838
https://doi.org/10.1007/978-3-030-63416-2_838
Autor:
Tae Hyun Kim, Kyoung Mu Lee
Publikováno v:
Computer Vision ISBN: 9783030032432
Computer Vision
Computer Vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::045736910a4c2b0a92915b746d2de134
https://doi.org/10.1007/978-3-030-03243-2_839-1
https://doi.org/10.1007/978-3-030-03243-2_839-1
Whole-body 3D human mesh estimation aims to reconstruct the 3D human body, hands, and face simultaneously. Although several methods have been proposed, accurate prediction of 3D hands, which consist of 3D wrist and fingers, still remains challenging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a2162d2c938b3889ec6626b31272f01
http://arxiv.org/abs/2011.11534
http://arxiv.org/abs/2011.11534
Autor:
Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee, Yu Tseng, Yu-Syuan Xu, Cheng-Ming Chiang, Yi-Min Tsai, Stephan Brehm, Sebastian Scherer, Dejia Xu, Yihao Chu, Qingyan Sun, Jiaqin Jiang, Lunhao Duan, Jian Yao, Kuldeep Purpohit, Maitreya Suin, A.N. Rajagopalan, Yuichi Ito, P.S. Hrishikesh, Densen Puthussery, K.A. Akhil, C.V. Jiji, Guisik Kim, P.L. Deepa, Zhiwei Xiong, Jie Huang, Dong Liu, Sangmin Kim, Hyungjoon Nam, Jisu Kim, Jechang Jeong, Shihua Huang, Yuchen Fan, Jiahui Yu, Haichao Yu, Thomas S. Huang, Ya Zhou, Xin Li, Sen Liu, Zhibo Chen, Saikat Dutta, Sourya Dipta Das, Shivam Garg, Daniel Sprague, Bhrij Patel, Thomas Huck
Publikováno v:
CVPR Workshops
Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring. In this challenge, we present the evaluation results from 3 competition tracks as wel
Publikováno v:
ICASSP
In this paper, we estimate depth information using two defocused images from dual aperture camera. Recent advances in deep learning techniques have increased the accuracy of depth estimation. Besides, methods of using a defocused image in which an ob
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)
ECCV (7)
Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image. The first weakness of these methods is the overfitting to image a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c602b9686f830d8ee002c50231739374
https://doi.org/10.1007/978-3-030-58571-6_45
https://doi.org/10.1007/978-3-030-58571-6_45
Publikováno v:
CVPR
Despite the recent success of single image-based 3D human pose and shape estimation methods, recovering temporally consistent and smooth 3D human motion from a video is still challenging. Several video-based methods have been proposed; however, they
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::92a7766ea1885f985413fea0632953ac
Autor:
Yu Qiao, Munchurl Kim, Yihao Liu, Norimichi Ukita, Wonyong Seo, Wenhao Zhang, Pablo Navarrete Michelini, Radu Timofte, Li Siyao, Kazutoshi Akita, Jaerin Lee, Wenxiu Sun, Chao Dong, Kyoung Mu Lee, Liangbin Xie, Seungjun Nah, Woonsung Park, Sanghyun Son
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030668228
ECCV Workshops (4)
ECCV Workshops (4)
Videos in the real-world contain various dynamics and motions that may look unnaturally discontinuous in time when the recorded frame rate is low. This paper reports the second AIM challenge on Video Temporal Super-Resolution (VTSR), a.k.a. frame int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e7db56dd6705645a28e1d25f7c8ed9f
https://doi.org/10.1007/978-3-030-66823-5_2
https://doi.org/10.1007/978-3-030-66823-5_2
Most 3D human mesh regressors are fully supervised with 3D pseudo-GT human model parameters and weakly supervised with GT 2D/3D joint coordinates as the 3D pseudo-GTs bring great performance gain. The 3D pseudo-GTs are obtained by annotators, systems
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfec874af560a06222d48e3796ec57fb
Autor:
Kyoung Mu Lee, Gyeongsik Moon
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)
ECCV (7)
Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image. However, directly regressing the parameters from the input image is a highly non-linear mapping because it bre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d115486b4bdb579bb61746d8492a441a
https://doi.org/10.1007/978-3-030-58571-6_44
https://doi.org/10.1007/978-3-030-58571-6_44