• Infrared and Laser Engineering
  • Vol. 49, Issue 10, 20200273 (2020)
Xuejing Qiu1、2、3, Wang Zhao1、2, Chao Yang1、2、3, Tao Cheng1、2、3, Shuai Wang1、2, and Bing Xu1、2
Author Affiliations
  • 1Key Laboratory of Adaptive Optics, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China
  • 2Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China
  • 3University of Chinese Academy of Sciences, Beijing 100049, China
  • show less
    DOI: 10.3788/IRLA20200273 Cite this Article
    Xuejing Qiu, Wang Zhao, Chao Yang, Tao Cheng, Shuai Wang, Bing Xu. A single-frame deep learning phase retrieval algorithm based on defocus grating[J]. Infrared and Laser Engineering, 2020, 49(10): 20200273 Copy Citation Text show less
    Optical properties(a) and schematic diagram(b) of defocus grating
    Fig. 1. Optical properties(a) and schematic diagram(b) of defocus grating
    Far-field intensity distribution acquired by CCD (b1) and corresponding positive defocus spots (b2), focal plane spots (b3), negative defocus spots (b4) when incident aberration is (a)
    Fig. 2. Far-field intensity distribution acquired by CCD (b1) and corresponding positive defocus spots (b2), focal plane spots (b3), negative defocus spots (b4) when incident aberration is (a)
    Schematic diagram of single-frame deep learning PR algorithm based on defocus grating
    Fig. 3. Schematic diagram of single-frame deep learning PR algorithm based on defocus grating
    Schematic diagram of CNN architecture
    Fig. 4. Schematic diagram of CNN architecture
    A sample from training set(c) and corresponding label(b), corresponding incident wavefront(a)
    Fig. 5. A sample from training set(c) and corresponding label(b), corresponding incident wavefront(a)
    Reconstruction accuracy of 1 000 test samples
    Fig. 6. Reconstruction accuracy of 1 000 test samples
    Fitting results of Zernike coefficients, incident wavefront, predicted wavefront and residual wavefront of 30th sample and 799th samples in test set
    Fig. 7. Fitting results of Zernike coefficients, incident wavefront, predicted wavefront and residual wavefront of 30th sample and 799th samples in test set
    Reconstruction accuracy of another 500 samples
    Fig. 8. Reconstruction accuracy of another 500 samples
    Incident wavefront, wavefront predicted by CNN and residual wavefront corresponding to 19th-23rd Zernike modes
    Fig. 9. Incident wavefront, wavefront predicted by CNN and residual wavefront corresponding to 19th-23rd Zernike modes
    Xuejing Qiu, Wang Zhao, Chao Yang, Tao Cheng, Shuai Wang, Bing Xu. A single-frame deep learning phase retrieval algorithm based on defocus grating[J]. Infrared and Laser Engineering, 2020, 49(10): 20200273
    Download Citation