DC Field | Value | Language |
---|---|---|
dc.contributor.author | 차시헌 | ko |
dc.contributor.author | 노준용 | ko |
dc.contributor.author | 서광균 | ko |
dc.contributor.author | Ashtari, Amirsaman | ko |
dc.date.accessioned | 2022-09-20T06:00:27Z | - |
dc.date.available | 2022-09-20T06:00:27Z | - |
dc.date.created | 2022-09-14 | - |
dc.date.issued | 2022-07-14 | - |
dc.identifier.citation | 한국컴퓨터그래픽스학회 2022 학술대회, pp.125 - 126 | - |
dc.identifier.issn | 1975-7883 | - |
dc.identifier.uri | http://hdl.handle.net/10203/298652 | - |
dc.description.abstract | Generating the texture map for a 3D human mesh from a single image is challenging. To generate a plausible texture map, the invisible part of the texture needs to be synthesized with relevance to the visible part and the texture should semantically align to the UV space of the template mesh. To overcome such challenges, we propose a novel method that incorporates SamplerNet and RefinerNet. SamplerNet predicts a sampling grid that enables sampling from the given visible texture information, and RefinerNet refines the sampled texture to maintain spatial alignment. | - |
dc.language | English | - |
dc.publisher | (사)한국컴퓨터그래픽스학회 | - |
dc.title | 샘플링과 정규화를 통한 단일 이미지로부터 3D 인물 텍스처 생성 | - |
dc.title.alternative | Generating 3D Human Texture from a Single Image with Sampling and Refinement | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 125 | - |
dc.citation.endingpage | 126 | - |
dc.citation.publicationname | 한국컴퓨터그래픽스학회 2022 학술대회 | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | 속초, 대명델피노리조트 | - |
dc.contributor.localauthor | 노준용 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.