Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to sequentially fuse feature maps of input images. However, RNN-based app...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	International journal of computer vision Jg. 128; H. 12; S. 2919 - 2935
Hauptverfasser:	Xie, Haozhe, Yao, Hongxun, Zhang, Shengping, Zhou, Shangchen, Sun, Wenxiu
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.12.2020 Springer
Schlagworte:	Artificial Intelligence Computer Imaging Computer Science Image Processing and Computer Vision Neural networks Pattern Recognition Pattern Recognition and Graphics Vision Multi-scale Context-aware Convolutional neural network 3D object reconstruction
ISSN:	0920-5691, 1573-1405
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!