Extended Data Fig. 4: Ablation study on ground truth data for 3μm polystyrene beads. | Nature Machine Intelligence

Extended Data Fig. 4: Ablation study on ground truth data for 3μm polystyrene beads.

From: Deep learning based on parameterized physical forward model for adaptive holographic imaging with unpaired data

Extended Data Fig. 4

The proposed network was trained with whole diffraction intensity data (3600 patches) while decreasing the portion of the complex amplitude data as 100%, 10%, 1%, and 0.5%. a,b, The diffraction intensity measured at (a) 9 mm and (b) 15 mm are used as the network input. The proposed approach consistently generates the complex amplitude maps up to the level where 1% (~60 patches) of complex amplitude data are used for training. Scale bar: 20 μm.

Back to article page