Abstract | ||
---|---|---|
•We propose an end-to-end method for Multispectral Photometric Stereo, without any extra information.•For the first time, our MPS-Net takes the initial surface normal into account, which provides a state-of-the-art estimation.•We design a localized convolutional neural network to establish flexible mapping considering the adjacent structural feature. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neucom.2019.09.084 | Neurocomputing |
Keywords | Field | DocType |
Surface normal estimation,Multispectral photometric stereo,Neural network | Colored,Pattern recognition,Multispectral image,Artificial intelligence,Reflectivity,Limiting,Normal,Photometric stereo,Mathematics,Calibration | Journal |
Volume | ISSN | Citations |
375 | 0925-2312 | 2 |
PageRank | References | Authors |
0.38 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yakun Ju | 1 | 9 | 3.26 |
Lin Qi | 2 | 27 | 8.68 |
Jichao He | 3 | 2 | 0.38 |
Xinghui Dong | 4 | 14 | 5.00 |
Feng Gao | 5 | 2 | 1.39 |
Junyu Dong | 6 | 99 | 23.43 |