Implementation "Adapting Auxiliary Losses Using Gradient Similarity" article
-
Updated
Mar 1, 2019 - Jupyter Notebook
Implementation "Adapting Auxiliary Losses Using Gradient Similarity" article
DDEGSM is a novel full-reference method that is developed to measure quality of screen content images by efficiently incorporating the effect of two challenging distortion types: contrast change (CC) and color saturation change (CSC).
Add a description, image, and links to the gradient-similarity topic page so that developers can more easily learn about it.
To associate your repository with the gradient-similarity topic, visit your repo's landing page and select "manage topics."