Fourier Ptychography probes the sample from different directions to achieve label-free quantitative phase imaging with a large space-bandwidth product. However, special attention has to be paid in the calibration of the optical setup to assure the accurate knowledge of the geometrical parameters involved in the image reconstruction. Any slight misalignment can provoke incorrect synthesis of the observables and, in turn, severe phase errors in the resulting high-resolution image. Here, we present a new processing pipeline that automatically removes such a priori unknown artifacts, thus making Fourier Ptychography miscalibration-tolerant. This result is achieved through a numerical Multi-Look approach that generates and combines multiple reconstructions of the same set of observables where phase artifacts are largely uncorrelated and, thus, automatically suppress each other. The proposed method is non-iterative, fully parallelizable, and completely blind, unlocking the use of Fourier Ptychography as an easy to handle tool or add-on to existing microscopes to be employed by unskilled users, thus paving the way to biomedical and clinical practices.

In this work, we propose CBiGAN - a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fairly good modeling power and reconstruction consistency capability. We evaluate the proposed method on MVTec AD - a real-world benchmark for unsupervised anomaly detection on high-resolution images - and compare against standard baselines and state-of-the-art approaches. Experiments show that the proposed method improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. We also observe that our model is particularly effective in texture-type anomaly detection, as it sets a new state of the art in this category. Our code is available at https://github.com/fabiocarrara/cbigan-ad/.