DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Dae-Shik | - |
dc.contributor.advisor | 김대식 | - |
dc.contributor.author | Kim, Deokyun | - |
dc.date.accessioned | 2021-05-13T19:32:57Z | - |
dc.date.available | 2021-05-13T19:32:57Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911311&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284702 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[iii, 21 p. :] | - |
dc.description.abstract | Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images. The main challenge of face SR is to restore essential facial features without distortion. We propose a novel face SR method that generates photo-realistic 8$\times$ super-resolved face images with fully retained facial details. To that end, we adopt a progressive training method, which allows stable training by splitting the network into successive steps, each producing output with a progressively higher resolution. We also propose a novel facial attention loss and apply it at each step to focus on restoring facial attributes in greater details by multiplying the pixel difference and heatmap values. Lastly, we propose a compressed version of the state-of-the-art Face Alignment Network (FAN) for landmark heatmap extraction. With the proposed FAN, we can extract the heatmaps suitable for face SR and also reduce the overall training time. Experimental results verify that our method outperforms state-of-the-art methods in both qualitative and quantitative measurements, especially in perceptual quality. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep Learning▼aComputer Vision▼aSuper-Resolution▼aImage Processing▼aGenerative Model | - |
dc.subject | 딥러닝▼a컴퓨터 비전▼a초해상도 복원▼a이미지 처리▼a생성 모델 | - |
dc.title | Deep learning based progressive face super-resolution via attention to facial landmarks | - |
dc.title.alternative | 심층학습 기반 얼굴 랜드마크 집중을 통한 점진적 얼굴 고해상도 복원 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김덕윤 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.