DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Park, Jinah | - |
dc.contributor.advisor | 박진아 | - |
dc.contributor.author | Kim, Hyunsoo | - |
dc.date.accessioned | 2022-04-27T19:31:58Z | - |
dc.date.available | 2022-04-27T19:31:58Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948446&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296117 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iii, 28 p. :] | - |
dc.description.abstract | In this thesis, I propose $\textit{Soft Voxelizer}$, a differentiable voxelizer that can be used in 3D geometry processing tasks involving both meshes and voxel images. By generating softened voxelization results, Soft Voxelizer allows gradients with respect to voxels to propagate across the voxelizer, enabling mesh-side optimization from voxel-side loss functions. With a softness hyperparameter, it also provides some controls over the loss landscape for fast and optimal convergence. Using the proposed voxelizer, one can iteratively deform a base mesh to fit a given voxel image through the gradient descent. Experiments also demonstrate that a medical image segmentation network can be trained on the mesh-side with the loss defined on the voxel-side. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Geometry processing▼adifferentiable programming▼a3D representations▼avoxelization | - |
dc.subject | 기하 처리▼a미분 가능한 프로그래밍▼a3차원 표현▼a복셀화 | - |
dc.title | Soft Voxelizer: a differentiable voxelizer for multi-representational 3D geometry processing | - |
dc.title.alternative | Soft Voxelizer: 다중 표현 3차원 기하 처리를 위한 미분 가능한 복셀라이저 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 김현수 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.