https://scholars.lib.ntu.edu.tw/handle/123456789/607102
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Chen S.-L | en_US |
dc.contributor.author | Shih K.-T | en_US |
dc.contributor.author | Chen H.H. | en_US |
dc.contributor.author | HOMER H. CHEN | en_US |
dc.creator | Chen S.-L;Shih K.-T;Chen H.H. | - |
dc.date.accessioned | 2022-04-25T06:42:13Z | - |
dc.date.available | 2022-04-25T06:42:13Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124177358&doi=10.1109%2fAIVR52153.2021.00017&partnerID=40&md5=def31332ac45dac876f9039fa814f441 | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/607102 | - |
dc.description.abstract | We propose an unsupervised learning framework trained with a small dataset for 3D object reconstruction from a single image. Our method utilizes autoencoders to extract 3D knowledge from an image, a differentiable renderer to generate an image from a reconstructed 3D object, and GAN inversion to produce pseudo images with random viewpoints and lighting to enlarge the training dataset. Quantitative and qualitative experimental results prove that our approach can recover 3D shapes with small dataset as accurately as state-of-the-art networks with large dataset. ? 2021 IEEE | - |
dc.relation.ispartof | Proceedings - 2021 4th IEEE International Conference on Artificial Intelligence and Virtual Reality, AIVR 2021 | - |
dc.subject | 3D object reconstruction | - |
dc.subject | Data augmentation | - |
dc.subject | GAN inversion | - |
dc.subject | Unsupervised learning | - |
dc.subject | Computer vision | - |
dc.subject | Image reconstruction | - |
dc.subject | Large dataset | - |
dc.subject | 3-D object reconstruction | - |
dc.subject | 3-D shape | - |
dc.subject | 3D object | - |
dc.subject | Auto encoders | - |
dc.subject | Single images | - |
dc.subject | Small data set | - |
dc.subject | State of the art | - |
dc.subject | Training dataset | - |
dc.title | Unsupervised Learning of 3D Object Reconstruction with Small Dataset | en_US |
dc.type | conference paper | en |
dc.identifier.doi | 10.1109/AIVR52153.2021.00017 | - |
dc.identifier.scopus | 2-s2.0-85124177358 | - |
dc.relation.pages | 54-59 | - |
item.cerifentitytype | Publications | - |
item.fulltext | no fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.openairetype | conference paper | - |
item.grantfulltext | none | - |
crisitem.author.dept | Communication Engineering | - |
crisitem.author.dept | Electrical Engineering | - |
crisitem.author.dept | Networking and Multimedia | - |
crisitem.author.orcid | 0000-0002-8795-1911 | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。