DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kweon, In So | - |
dc.contributor.advisor | 권인소 | - |
dc.contributor.author | Shim, Gyumin | - |
dc.date.accessioned | 2021-05-13T19:33:35Z | - |
dc.date.available | 2021-05-13T19:33:35Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911346&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284737 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[iv, 34 p. :] | - |
dc.description.abstract | In computer vision, various two-image input based tasks including stereo vision, optical-flow estimation have been actively researched. As deep learning architectures are trained on a large-scale dataset to extract fundamental features, extracting the most general correspondence requires a specific dataset to learn. In this paper, in order to learn the most fundamental correspondences, we solve reference based super resolution (RefSR) selecting a dataset containing various correspondences. We propose a correspondence searching and extracting network (CSENet) and prove its utility solving RefSR, self-similarity SR, and sensor fusion. CSENet is able to handle small and large displacements with dynamic offset estimator for deformable convolution and robustly extract correspondences with relevancy-aware weight learning for cluttered or irrelevant input data. The proposed network is end-to-end trainable without any additional supervisions or heavy computations. Experimental results demonstrate a superior performance of the proposed method compared to previous works quantitatively and qualitatively. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Reference based Super Resolution▼aDeformable Convolution▼aSelf-similarity Super Resolution▼aSensor Fusion | - |
dc.subject | 근거 기반 초해상도 | - |
dc.subject | 가변형 컨볼루션 | - |
dc.subject | 자기 참조 초해상도 | - |
dc.subject | 센서 융합 | - |
dc.title | Deep learning architecture for two-image analysis via reference based super resolution | - |
dc.title.alternative | 근거 기반 초해상도 기법을 통한 두 장의 영상 분석 딥러닝 아키텍쳐 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 심규민 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.