Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 임종우 | - |
dc.date.accessioned | 2020-10-05T02:37:41Z | - |
dc.date.available | 2020-10-05T02:37:41Z | - |
dc.date.issued | 2019-10 | - |
dc.identifier.citation | 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Page. 8986-8996 | en_US |
dc.identifier.isbn | 978-1-7281-4803-8 | - |
dc.identifier.issn | 2380-7504 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/9010863 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/154350 | - |
dc.description.abstract | In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on an omnidirectional rig are processed by the feature extraction module, and then the deep feature maps are warped onto the concentric spheres swept through all candidate depths using the calibrated camera parameters. The 3D encoder-decoder block takes the aligned feature volume to produce the omnidirectional depth estimate with regularization on uncertain regions utilizing the global context information. In addition, we present large-scale synthetic datasets for training and testing omnidirectional multi-view stereo algorithms. Our datasets consist of 11K ground-truth depth maps and 45K fisheye images in four orthogonal directions with various objects and environments. Experimental results show that the proposed method generates excellent results in both synthetic and real-world environments, and it outperforms the prior art and the omnidirectional versions of the state-of-the-art conventional stereo algorithms. | en_US |
dc.description.sponsorship | This research was supported by Next-Generation Information Computing Development program through National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT (NR-2017M3C4A7069369), the NR grant funded by the Korea govemment (MSIP)(NRF-2017RlA2B4011928), Research Fellow program funded by the Korea government (NRF- 2017RlA6A3A11031193), and Samsung Research Funding & Incubation Center for Future Technology (SRFC-TC1603-05). | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE/CVF | en_US |
dc.subject | Cameras | en_US |
dc.subject | Feature extraction | en_US |
dc.subject | Three-dimensional displays | en_US |
dc.subject | Estimation | en_US |
dc.subject | Neural networks | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Computational modeling | en_US |
dc.title | OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1109/ICCV.2019.00908 | - |
dc.relation.page | 8987-8996 | - |
dc.contributor.googleauthor | Won, Changhee | - |
dc.contributor.googleauthor | Ryu, Jongbin | - |
dc.contributor.googleauthor | Lim, Jongwoo | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF COMPUTER SCIENCE | - |
dc.identifier.pid | jlim | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.