Fig. 1. Diagram of blockwise/parallel compressive imaging system^[19]

Fig. 2. Diagram of MWIR blockwsie compressive imaging system^[43]

Fig. 3. Integral optical machine used for incidence and reflection of DMD^[43]

Fig. 4. Diagram of compressive sensing pulse laser ranging system using PIN^[54]

Fig. 5. Diagram of compressive sensing pulse laser ranging system using TCSPC module^[57]

Fig. 6. LiDAR 3D imaging with gated compressive sensing ^[56]

Fig. 7. Diagram of compressive sensing phase laser ranging system^[60]

Fig. 8. Diagram of compressive sensing low-bandwidth pulse laser ranging system^[61]

Fig. 9. Diagram of temporal super-resolution full waveform LiDAR system ^[62]

Fig. 10. Experimental results of temporal super-resolution full waveform LiDAR^[62]

Fig. 11. Comparison of concepts of spatial compressive imaging and temporal compressive imaging. (a) Spatial compressive imaging; (b) temporal compressive imaging

Fig. 12. Experimental results of dual-band temporal compressive imaging. (a) 1 frame measured value in visible band; (b) 10 frame reconstructed images in visible band; (c) reconstructed images of 1 frame in IR band; (d) 10 frame reconstructed images in IR band

Fig. 13. Ultra-fast camera using compressive imaging^[75]

Fig. 14. CASSI system. (a) CASSI system diagram; (b) CASSI data collection diagram^[77]

Fig. 15. SSCSI system diagram^[79]

Fig. 16. Diagram of ghost-imaging system of pseudothermal source^[89]

Fig. 17. Diagram of computational ghost imaging system^[89]

Fig. 18. 3D process of Gabor hologram^[104]

Fig. 19. Deep learning network used in spatial compressive imaging system. (a) Structural diagram of ReconNet unit; (b) flow diagram for ReconNet^[113]

Fig. 20. Flowchart of GI using deep neural networks^[102]

Fig. 21. Framework of GI using deep neural networks^[102]

Fig. 22. Schematic of training progress of proposed end-to-end deep learning ghost imaging^[103]

Fig. 23. Neural network architecture for image restoration based on end-to-end deep learning ghost imaging^[103]