https://scholars.lib.ntu.edu.tw/handle/123456789/607102
標題: | Unsupervised Learning of 3D Object Reconstruction with Small Dataset | 作者: | Chen S.-L Shih K.-T Chen H.H. HOMER H. CHEN |
關鍵字: | 3D object reconstruction;Data augmentation;GAN inversion;Unsupervised learning;Computer vision;Image reconstruction;Large dataset;3-D object reconstruction;3-D shape;3D object;Auto encoders;Single images;Small data set;State of the art;Training dataset | 公開日期: | 2021 | 起(迄)頁: | 54-59 | 來源出版物: | Proceedings - 2021 4th IEEE International Conference on Artificial Intelligence and Virtual Reality, AIVR 2021 | 摘要: | 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 |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124177358&doi=10.1109%2fAIVR52153.2021.00017&partnerID=40&md5=def31332ac45dac876f9039fa814f441 https://scholars.lib.ntu.edu.tw/handle/123456789/607102 |
DOI: | 10.1109/AIVR52153.2021.00017 |
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。