AI RESEARCH

Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference

arXiv CS.LG

ArXi:2509.25269v2 Announce Type: replace-cross In this work, we present and investigate the novel blind inverse problem of position-blind ptychography, i.e., ptychographic phase retrieval without any knowledge of scan positions, which then must be recovered jointly with the image. The motivation for this problem comes from single-particle diffractive X-ray imaging, where particles in random orientations are illuminated and a set of diffraction patterns is collected.