Fig. 1. Optical properties(a) and schematic diagram(b) of defocus grating

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)

Fig. 3. Schematic diagram of single-frame deep learning PR algorithm based on defocus grating

Fig. 4. Schematic diagram of CNN architecture

Fig. 5. A sample from training set(c) and corresponding label(b), corresponding incident wavefront(a)

Fig. 6. Reconstruction accuracy of 1 000 test samples

Fig. 7. Fitting results of Zernike coefficients, incident wavefront, predicted wavefront and residual wavefront of 30th sample and 799th samples in test set

Fig. 8. Reconstruction accuracy of another 500 samples

Fig. 9. Incident wavefront, wavefront predicted by CNN and residual wavefront corresponding to 19th-23rd Zernike modes