Method and system for enhancing images using machine learning

Method for enhancing images for metrological applications comprising:

• providing a first set comprising at least one first image, the first set in particular being a first sequence, wherein the first images are sensor images, wherein the first set represents a scene of interest, and providing a second set comprising at least one second image, the second set in particular being a second sequence, wherein the second images are sensor images, wherein the second set represents at least a part of the scene of interest, wherein the at least one first image and the at least one second image differ geometrically,
• wherein a position and/or an orientation of at least one object within the scene of interest is determinable from the first set and/or from the second set with an initial precision,
• jointly processing the first set and the second set by a neural network, and
• outputting a third set, the third set in particular being a third sequence, of images by the neural network, the third set comprising at least one processed image, from which is determinable the position and/or orientation of the at least one object with a processed precision, wherein the processed precision is equal to or higher than the initial precision.