Deep learning architecture for two-image analysis via reference based super resolution근거 기반 초해상도 기법을 통한 두 장의 영상 분석 딥러닝 아키텍쳐

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 141
  • Download : 0
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.
Advisors
Kweon, In Soresearcher권인소researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2020
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[iv, 34 p. :]

Keywords

Reference based Super Resolution▼aDeformable Convolution▼aSelf-similarity Super Resolution▼aSensor Fusion; 근거 기반 초해상도; 가변형 컨볼루션; 자기 참조 초해상도; 센서 융합

URI
http://hdl.handle.net/10203/284737
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911346&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0