A method includes training a first model to measure the banding artefacts (1302), training a second model to deband the image (1304), and generating a debanded image for the image using the second model (1306). Training the first model (1302) can include selecting a first set of first training images, generating a banding edge map for a first training image, where the map includes weights that emphasize banding edges and de-emphasize true edges in the first training image, and using the map and a luminance plane of the first training image as input to the first model. Training the second model (1304) can include selecting a second set of second training images, generating a debanded training image for a second training image, generating a banding score for the debanded training image using the first model, and using the banding score in a loss function used in the training the second model..