DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoon, Sung-Eui | - |
dc.contributor.advisor | 윤성의 | - |
dc.contributor.author | Kim, Kyuyeon | - |
dc.date.accessioned | 2023-06-26T19:31:35Z | - |
dc.date.available | 2023-06-26T19:31:35Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997568&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309555 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2022.2,[iv, 21 p. :] | - |
dc.description.abstract | Humans can easily imagine a scene from auditory information based on their prior knowledge of audio-visual events. In this paper, we mimic this innate human ability in deep learning models to improve the quality of video inpainting. To implement the prior knowledge, we first train the audio-visual network to learn the correspondence between auditory and visual information. Then, the audio-visual network is employed as a guider that conveys the prior knowledge of audio-visual correspondence to the video inpainting network. This prior knowledge is transferred through our proposed two novel losses – audio-visual attention loss and audio-visual pseudo-class consistency loss – that further improve the performance of the video inpainting network. These two losses encourage the inpainting result to have a high correspondence to its synchronized audio. Experimental results demonstrate that our proposed method can restore a wider domain of video scenes and is particularly effective when the sounding object in the scene is partially blinded. This thesis is based on the author’s original paper [1]. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Deep video inpainting guided by audio-visual self-supervision | - |
dc.title.alternative | 시청각적 자기지도를 통한 심층 비디오 인페인팅 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 김규연 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.