DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 최성희 | - |
dc.contributor.author | Min, Youngjo | - |
dc.contributor.author | 민영조 | - |
dc.date.accessioned | 2024-07-25T19:31:23Z | - |
dc.date.available | 2024-07-25T19:31:23Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045948&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320716 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2023.8,[iii, 21 p. :] | - |
dc.description.abstract | Shape correspondence is a problem finding correspondences between two given 3d shapes. In this work, we introduce a new surface learning model, VDN, to solve the shape correspondence problem. Our model consists of two main features, diffusion and anisotropic operators. Diffusion spreads the data in the spatial dimension, so all points get the nearby information. In this manner, diffusion is used as the generalization of the convolution to curved surfaces. However, the convolution filters are restricted to be symmetric. Our model broadens the possible convolutions using the anisotropic operators from additionally learning vectors. In this way, experiments show that our method has better result than the based model. Furthermore, using only the geometric operators to communicate spatially, our model is discretization agnostic. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 형상 대응▼a함수간 함수▼a기하 딥 러닝▼a지도 학습▼a텍스처 이전 | - |
dc.subject | Shape correspondence▼aFunctional map▼aGeometric deep learning▼aSupervised learning▼aTexture transfer | - |
dc.title | Learning with diffusion and anisotropic operators for shape correspondence | - |
dc.title.alternative | 형상 대응 문제를 위한 확산과 비등방성 연산자를 사용한 학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | Choi, Sunghee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.