Differentiable end-to-End Pixel-Super-Resolution Lensless Imaging

A differentiable Pixel-Super-Resolution (dPSR) lensless imaging system comprising:

• a light source emitting a beam of light;
• a sensor positioned to receive the beam of light;
• a platform for a sample or target located between the light source and the sensor, where the distance between the light source and the platform is much greater than the distance between the platform and the sensor, and the sensor receives light from the light source that has passed through a sample on the platform in the form of iterations that form a series of images of the sample at a series of angles;
• and
• a computer that accepts the series of images from the sensor and reconstructs a full holographic image of the target at a higher resolution than the sensor, by integrating differentiable PSR image hologram synthesis, autofocusing, and complex-field sample reconstruction with an inverse problem-solving algorithm into a single unified end-to-end framework representing the numerical forward model of the lensless system, whereby automatic differentiation causes simultaneous reconstruction of (a) the complex field representing the sample, (b) the subpixel shift scanning positions, and (c) the sample-to-sensor distance using gradient descent optimization.