Deep Learning Based Single-Photon 3D Imaging with Multiple Returns
| Autor: | Yu Hong, Jiayong Peng, Dong Liu, Feihu Xu, Zheng-Ping Li, Zhiwei Xiong, Hao Tan, Xin Huang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Deblurring
Computer science business.industry Deep learning Field of view 02 engineering and technology Iterative reconstruction 021001 nanoscience & nanotechnology 01 natural sciences Convolutional neural network 010309 optics Background noise Depth map Distortion 0103 physical sciences Computer vision Artificial intelligence 0210 nano-technology business |
| Zdroj: | 3DV |
| Popis: | photon avalanche diode (SPAD) has been widely used in active 3D imaging due to its extremely high photon sensitivity and picosecond time resolution. However, long-range active 3D imaging is still a great challenge, since only a few signal photons mixed with strong background noise can return from multiple reflectors of the scene due to the divergence of the light beam and the receiver’s field of view (FoV), which would bring considerable distortion and blur to the recovered depth map. In this paper, we propose a deep learning based depth reconstruction method for long range single-photon 3D imaging where the “multiple-returns” issue exists. Specifically, we model this problem as a deblurring task and design a multi-scale convolutional neural network combined with elaborate loss functions, which promote the reconstruction of an accurate depth map with fine details and clear boundaries of objects. The proposed method achieves superior performance over several different sizes of receiver’s FoV on a synthetic dataset compared with existing state-of-the-art methods and the trained model under a specific FoV has a strong generalization capability across different sizes of FoV, which is essential for practical applications. Moreover, we conduct outdoor experiments and demonstrate the effectiveness of our method in a real-world long range imaging system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|