| CPC H04N 23/88 (2023.01) [G06T 7/90 (2017.01); G06N 3/0985 (2023.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01)] | 15 Claims |
|
1. A processing entity, the processing entity configured to:
generate a model for estimating scene illumination colour for a source image captured by a camera, the model generation comprising:
acquiring a set of images, each image of the set of images having been captured by a respective camera, the set of images as a whole comprising images captured by multiple cameras;
forming a set of tasks by assigning each image of the set of images to a respective task such that images in a same task have in common that a property of the images lies in a predetermined range, wherein the predetermined range corresponds to a set of colour temperatures of the respective image or the respective camera that captured the respective image, and wherein images captured by each camera are allocated to different tasks if colour temperatures of the images are substantially different; and
training parameters of the model by repeatedly:
selecting at least one of the tasks,
forming an interim set of model parameters in dependence on a first subset of the images of that task,
estimating a quality of the interim set of model parameters against a second subset of the images of that task, and
updating the parameters of the model in dependence on the interim set of parameters and the estimated quality.
|