Publications
Detailed Information
Style Transfer Learning using Image Segmentation Awareness : 이미지 분할 인식을 이용한 스타일 전이 학습
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이재욱 | - |
dc.contributor.author | 차민철 | - |
dc.date.accessioned | 2018-05-29T03:21:11Z | - |
dc.date.available | 2018-05-29T03:21:11Z | - |
dc.date.issued | 2018-02 | - |
dc.identifier.other | 000000149346 | - |
dc.identifier.uri | https://hdl.handle.net/10371/141444 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 공과대학 산업공학과, 2018. 2. 이재욱. | - |
dc.description.abstract | Recently, there are many studies in image style transfer. Image style transfer method transfers the style to the content image. However, it has a problem that it transfers the same style in different semantics. Thus, we proposed a new method named 'Segment style transfer'. Our method is composed of 4 phases: 'Image Segmentation', 'Segment Matching', 'Segment Style Transfer', and 'Segment Merging'. Our Segment style transfer method improves the existing image style transfer in that it does not make the transferred image heterogeneous and improve the image quality. | - |
dc.description.tableofcontents | Chapter 1 Introduction 1
1.1 Contributions 2 1.2 Related Work 3 Chapter 2 Image Style Transfer 7 2.1 Chapter Overview 7 2.2 Convolutional Neural Network 8 2.2.1 Convolutional layer 8 2.2.2 Pooling layer 9 2.2.3 Backpropagation 9 2.3 Content Reconstruction 11 2.4 Style Reconstruction 12 2.5 Image Style Transfer 13 Chapter 3 SegNet 15 3.1 Chapter Overview 15 3.2 Fully Convolutional Network 16 3.3 Encoder Network 17 3.4 Decoder Network 17 Chapter 4 Segment Style Transfer 19 4.1 Image Segmentation 19 4.2 Segment Matching 21 4.3 Segment Style Transfer 23 4.4 Segment Merging 25 4.5 Experimental results 26 Chapter 5 Conclusion 31 5.1 Summary of research 31 5.2 Implication of our work 32 Appendix A 33 Bibliography 35 국문초록 39 | - |
dc.format | application/pdf | - |
dc.format.extent | 9526816 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | Segment style transfer | - |
dc.subject | Pixel-wise segmentation | - |
dc.subject | Segment matching | - |
dc.subject | Image reconstruction | - |
dc.subject.ddc | 670.42 | - |
dc.title | Style Transfer Learning using Image Segmentation Awareness | - |
dc.title.alternative | 이미지 분할 인식을 이용한 스타일 전이 학습 | - |
dc.type | Thesis | - |
dc.description.degree | Master | - |
dc.contributor.affiliation | 공과대학 산업공학과 | - |
dc.date.awarded | 2018-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.