Automatic adaptation to image processing pipeline

摘要

Techniques are disclosed relating to generating generic labels, translating generic labels to image pipeline-specific labels, and automatically adjusting images. In one embodiment, generic labels may be generated. Generic algorithm parameters may be generated based on training a regression algorithm with the generic labels. The generic labels may be translated to pipeline-specific labels, which may be usable to automatically adjust an image.

主权项

1. A method implemented by one or more computing devices, the method comprising:
globally adjusting one or more parameters of an image by a particular image processing pipeline of a plurality of image processing pipelines based on a plurality of pipeline-specific labels and a plurality of generic algorithm parameters that are generated from a plurality of generic labels, the generic labels relating one or more parameters of a first image to a corresponding adjusted image of an image pair for each of a plurality of image pairs, the plurality of pipeline-specific labels of the particular image processing pipeline being different than a corresponding plurality of pipeline-specific labels of a different image processing pipeline; and causing output of the adjusted new image in a user interface.