Fig. 1. Data flow chart of the AL+DL algorithm. (a) Solver Sp(·) in a sparse domain; (b) general framework by connecting each iteration in a sequence order. Here, each Si(·) is calculated in parallel to producing Wi, and GD algorithm is employed to calculate I.

Fig. 2. (a) U-net architecture in the AL+DL algorithm; (b) self-attention model.

Fig. 3. Reconstructed results of (a) boatman, (b) ocean animal, and (c) finger by the AL+DL (second row), AL (third row), and TwIST (fourth row) algorithms, together with the ground truth (first row) for comparison. The last column is the enlarged image in the corresponding red squares.

Fig. 4. System configuration of CUP. DMD, digital micromirror device; CMOS, complementary metal–oxide-semiconductor.

Fig. 5. Measuring temporal evolution of a spatially modulated picosecond laser spot. (a) Experimental design. (b)–(d) Reconstructed results by the AL+DL, AL, and TwIST algorithms, respectively. (e) Measured static image by external CCD. (f)–(h) Extracted images from (b)–(d), respectively, at the time of 14 ps; curves on the right are the integration results of the corresponding images along the horizontal direction.

Fig. 6. Measuring wavefront movement by obliquely illuminating a collimated femtosecond laser pulse on a transverse fan pattern. (a) Experimental design. (b)–(d) Reconstructed results by the AL+DL, AL, and TwIST algorithms, respectively. (e) Measured static image by external CCD. (f)–(h) Integrated images from (b)–(d), respectively. (i)–(l) Results of Fourier transform from (e)–(h), respectively.

Table 1. Average PSNR (in dB) and SSIM by Different Image Reconstruction Algorithms in Different Dynamic Scenes