DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Dae-Shik | - |
dc.contributor.advisor | 김대식 | - |
dc.contributor.author | Cho, Wooyeong | - |
dc.date.accessioned | 2023-06-26T19:33:33Z | - |
dc.date.available | 2023-06-26T19:33:33Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997236&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309816 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2022.2,[iii, 18 p. :] | - |
dc.description.abstract | Burst image super-resolution is an ill-posed problem that aims to restore a high-resolution (HR) image from a sequence of low-resolution (LR) burst images. To restore a photo-realistic HR image using their abundant information, it is essential to align each burst of frames containing random hand-held motion. Some kernel prediction networks (KPNs) that are operated without external motion compensation such as optical flow estimation have been applied to burst image processing as implicit image alignment modules. However, the existing methods do not consider the interdependencies among the kernels of different sizes that have a significant effect on each pixel. In this paper, we propose a novel weighted multi-kernel prediction network (WMKPN) that can learn the discriminative features on each pixel for burst image super-resolution. Our experimental results demonstrate that WMKPN improves the visual quality of super-resolved images. To the best of our knowledge, it outperforms the state-of-the-art within kernel prediction methods and multiple frame super-resolution (MFSR) on both the Zurich RAW to RGB and BurstSR datasets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Deep learning based weighted multi-kernel prediction network for burst image super-resolution | - |
dc.title.alternative | 버스트 이미지 초고해상도 복원을 위한 심층학습 기반 가중치된 다중 커널 예측 네트워크 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 조우영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.