DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Choo, Jaegul | - |
dc.contributor.advisor | 주재걸 | - |
dc.contributor.author | Chung, Chaeyeon | - |
dc.date.accessioned | 2023-06-22T19:31:23Z | - |
dc.date.available | 2023-06-22T19:31:23Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008217&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308214 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.8,[iv, 24 p. :] | - |
dc.description.abstract | Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle. Although recent approaches significantly improved the hair details, this is achieved under the assumption that a target hair and a source image are aligned. HairFIT, a pose-invariant hairstyle transfer model, alleviates this assumption, yet it still shows unsatisfactory quality in preserving delicate hair textures. To solve these limitations, we propose a high-performing pose-invariant hairstyle transfer model equipped with a latent optimization and a newly presented local-style-matching loss. In the StyleGAN2 latent space, we first explore a pose-aligned latent code of a target hair with the detailed textures preserved based on local-style-matching. Then, our model inpaints the occlusions of the source considering the aligned target hair and blends both images to produce a final output. The experimental results demonstrate that our model has strengths in transferring a hairstyle under higher pose differences and preserving local hairstyle textures. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Hairstyle Transfer▼aLatent Optimization▼aConditional Image Generation▼aImage-to-Image Translation | - |
dc.subject | 헤어스타일 변환▼a잠재 공간 최적화▼a조건부 이미지 생성▼a이미지 변환 | - |
dc.title | Style your hair | - |
dc.title.alternative | 헤어스타일의 지역적 특징을 고려한 잠재 공간 최적화 기반 다양한 포즈에 강건한 헤어스타일 변환 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 정채연 | - |
dc.title.subtitle | latent optimization for pose-invariant hairstyle transfer via local-style-aware hair alignment | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.