DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 노준용 | - |
dc.contributor.author | Yoon, Soyeon | - |
dc.contributor.author | 윤소연 | - |
dc.date.accessioned | 2024-07-30T19:30:49Z | - |
dc.date.available | 2024-07-30T19:30:49Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096194&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321409 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 문화기술대학원, 2024.2,[iv, 34 p. :] | - |
dc.description.abstract | Recent advances in 3D face stylization have made significant strides in few to zero-shot settings. However, the degree of stylization achieved by existing methods is often not sufficient for practical applications because they are mostly based on statistical 3D Morphable Models (3DMM) with limited variations. To this end, we propose a method that can produce a highly stylized 3D face model with desired topology. Our methods train a surface deformation network with 3DMM and translate its domain to the target style using a single pair of 3D source face and target style mesh. The network achieves stylization of the 3D face to the style of the target using a differentiable renderer and directional CLIP losses. Additionally, during the inference process, we utilize a Mesh Agnostic Encoder (MAGE) to take as input a mesh of diverse topologies to the stylization process by encoding its shapes into our latent space. The resulting stylized face model can be animated by commonly used 3DMM blend shapes. A set of quantitative and qualitative evaluations demonstrate that our method can produce highly stylized face meshes according to a given style and outputs them in a desired topology. We also demonstrate example applications of our method including facial animation of stylized avatars and linear interpolation of geometric styles. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 표면 변형▼a3D 얼굴 생성▼a3D 얼굴 스타일화▼a3차원 변형 가능한 얼굴모델▼a토폴로지 애그노스틱 | - |
dc.subject | Surface deformation▼a3D face generation▼a3D face stylization▼a3DMM▼aTopology agnostic | - |
dc.title | LeGO: Leveraging a surface deformation network for animatable stylized face generation with one example | - |
dc.title.alternative | 표면 변형 네트워크를 활용한 하나의 예시 기반의 애니메이션 가능한 스타일화 된 얼굴 생성 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :문화기술대학원, | - |
dc.contributor.alternativeauthor | Noh, Junyong | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.