Most of the neural networks proposed so far for computational imaging (CI) in optics employ a supervised training strategy, and thus need a large training set to optimize their weights and biases.
Setting aside the requirements of environmental and system stability during many hours of data acquisition, in many practical applications, it is unlikely to be possible to obtain sufficient numbers of ground-truth images for training.
[Linking template=”default” type=”products” search=”102-P38″ header=”2″ limit=”190″ start=”2″ showCatalogNumber=”true” showSize=”true” showSupplier=”true” showPrice=”true” showDescription=”true” showAdditionalInformation=”true” showImage=”true” showSchemaMarkup=”true” imageWidth=”” imageHeight=””]