Scene-dependent adaptive compressive sensing (CS) has been a long pursuing goal that has huge potential to significantly improve the performance of CS. However, with no access to the ground truth, how to design the scene-dependent adaptive strategy is still an open problem. In this paper, a restricted isometry property (RIP) condition-based error-clamping is proposed, which could directly predict the reconstruction error, i.e., the difference between the current-stage reconstructed image and the ground truth image, and adaptively allocate more samples to regions with larger reconstruction error at the next sampling stage. Furthermore, we propose a CS reconstruction network composed of Progressively inverse transform and Alternating Bi-directional Multi-grid Network, named PiABM-Net, that could efficiently utilize the multi-scale information for reconstructing the target image. The effectiveness of the proposed adaptive and cascaded CS method is demonstrated with extensive quantitative and qualitative experiments, compared with the state-of-the-art CS algorithms.

Single-photon avalanche diodes (SPADs) are novel image sensors that record photons at extremely high sensitivity. To reduce both the required sensor area for readout circuits and the data throughput for SPAD array, in this paper, we propose a snapshot compressive sensing single-photon avalanche diode (CS-SPAD) sensor which can realize on-chip snapshot-type spatial compressive imaging in a compact form. Taking advantage of the digital counting nature of SPAD sensing, we propose to design the circuit connection between the sensing unit and the readout electronics for compressive sensing. To process the compressively sensed data, we propose a convolution neural-network-based algorithm dubbed CSSPAD-Net which could realize both high-fidelity scene reconstruction and classification. To demonstrate our method, we design and fabricate a CS-SPAD sensor chip, build a prototype imaging system, and demonstrate the proposed on-chip snapshot compressive sensing method on the MINIST dataset and real handwritten digital images, with both qualitative and quantitative results.