DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Mun Churl | - |
dc.contributor.advisor | 김문철 | - |
dc.contributor.author | Kim, Soo Ye | - |
dc.date.accessioned | 2019-09-04T02:40:20Z | - |
dc.date.available | 2019-09-04T02:40:20Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=828571&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266716 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2018.8,[iv, 38 p. :] | - |
dc.description.abstract | The demand for high quality videos has been increasing rapidly in recent years, and super-resolution (SR) methods are rising as core technologies for the generation of high quality visual content. SR methods can be mainly divided into two categories: single image SR and multi-frame (video) SR. While single image SR methods produce a single high resolution (HR) output from the corresponding single low resolution (LR) input, video SR methods produce a single HR output at a specific time instant from a series of consecutive LR input frames. Single image SR methods solely utilize the spatial information in a single input image to produce the HR output, whereas video SR methods exploit the temporal relations between the consecutive frames to make use of the additional spatial information available for a more accurate reconstruction of HR video frames. In this thesis, we present our research on video SR and propose a deep neural network-based HR frame generation method that considers scene changes when using the spatio-temporal information in video frame inputs. Furthermore, the proposed video SR method based on a 3D convolutional neural network does not require motion estimation nor compensation as a pre-processing step, which is often necessary for other video SR methods. We also present a scene boundary detection module and a frame input structure that prevents performance degradation due to scene changes in the input video frames. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | video super-resolution▼adeep learning▼aconvolutional neural networks | - |
dc.subject | 비디오 초해상화▼a딥러닝▼a심층 콘볼루션 신경망 | - |
dc.title | A study on video super-resolution using a 3D convolutional neural network with spatio-temporal feature extraction | - |
dc.title.alternative | 시공간 특징 추출의 3차원 콘볼루션 신경망을 이용한 비디오 초해상화에 관한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김수예 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.