Exploring Kolmogorov-Arnold networks for realistic image sharpness assessment
This work addresses image quality assessment for applications like photography or medical imaging, but it is incremental as it applies a recently developed method to a new domain.
The study tackled realistic image sharpness assessment by exploring Kolmogorov-Arnold networks (KANs), introducing TaylorKAN, and testing them on four databases; results showed KANs are competitive or superior to support vector regression, with TaylorKAN performing best using mid-level features.
Score prediction is crucial in evaluating realistic image sharpness based on collected informative features. Recently, Kolmogorov-Arnold networks (KANs) have been developed and witnessed remarkable success in data fitting. This study introduces the Taylor series-based KAN (TaylorKAN). Then, different KANs are explored in four realistic image databases (BID2011, CID2013, CLIVE, and KonIQ-10k) to predict the scores by using 15 mid-level features and 2048 high-level features. Compared to support vector regression, results show that KANs are generally competitive or superior, and TaylorKAN is the best one when mid-level features are used. This is the first study to investigate KANs on image quality assessment that sheds some light on how to select and further improve KANs in related tasks.