Fig. 1: Bright-field holography.

High-contrast bright-field imaging of a volumetric sample requires mechanical axial scanning and the acquisition of many successive images (e.g., N = 101 here spans ± 500 µm in depth). Bright-field holography, enabled by deep learning, fuses the volumetric imaging capability of holography with the speckle- and artifact-free image contrast of incoherent bright-field microscopy to generate bright-field equivalent images of a volume from a single hologram (N = 1 image)