摘要：Conventional imaging at low light levels requires hundreds of detected photons per pixel to suppress the Poisson noise for accurate reflectivity inference. We propose a high-efficiency photon-limited imaging technique, called fast first-photon ghost imaging, which recovers the image by conditional averaging of the reference patterns selected by the first-photon detection signal. Our technique merges the physics of low-flux measurements with the framework of computational ghost imaging. Experimental results demonstrate that it can reconstruct an image from less than 0.1 detected photon per pixel, which is three orders of magnitude less than conventional imaging techniques. A signal-to-noise ratio model of the system is established for noise analysis. With less data manipulation and shorter time requirements, our technique has potential applications in many fields, ranging from biological microscopy to remote sensing.
