Abstract | ||
---|---|---|
This paper presents Unsupervised Deep Shape from Template (UDSfT), a novel method that leverages deep neural networks (DNNs) for reconstructing the 3D surface of an object using a single image. More specifically, the reconstruction of isometric deformable objects is achieved in the proposed UDSfT method via a DNN-based template-based framework. Unlike previous approaches that leverage supervised learning, the proposed UDSfT method leverages the notion of unsupervised learning to overcome this obstacle and provide real-time 3D reconstruction. More specifically, UDSfT achieves this via an unsupervised structure that leverages a combination of real-data and synthetic data. Experimental results show that the proposed UDSfT method outperforms the state-of-the-art Shape from Template methods in object 3D reconstruction. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-27202-9_40 | IMAGE ANALYSIS AND RECOGNITION, ICIAR 2019, PT I |
Keywords | DocType | Volume |
Deep learning, Depth estimation, Shape from Template | Conference | 11662 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohammad Ali Bagheri Orumi | 1 | 0 | 0.34 |
M. Hadi Sepanj | 2 | 0 | 0.34 |
Mahmoud Famouri | 3 | 0 | 0.34 |
Zohreh Azimifar | 4 | 147 | 19.97 |
Alexander Wong | 5 | 351 | 69.61 |