Image Quality Assessment with Gradient Siamese Network
This work addresses image quality assessment for applications like image processing, but it is incremental as it builds on existing siamese network and attention methods.
The authors tackled full-reference image quality assessment by introducing the Gradient Siamese Network (GSN), which captures gradient features and uses multi-level fusion and KL divergence loss, achieving second place in the NTIRE 2022 challenge.
In this work, we introduce Gradient Siamese Network (GSN) for image quality assessment. The proposed method is skilled in capturing the gradient features between distorted images and reference images in full-reference image quality assessment(IQA) task. We utilize Central Differential Convolution to obtain both semantic features and detail difference hidden in image pair. Furthermore, spatial attention guides the network to concentrate on regions related to image detail. For the low-level, mid-level and high-level features extracted by the network, we innovatively design a multi-level fusion method to improve the efficiency of feature utilization. In addition to the common mean square error supervision, we further consider the relative distance among batch samples and successfully apply KL divergence loss to the image quality assessment task. We experimented the proposed algorithm GSN on several publicly available datasets and proved its superior performance. Our network won the second place in NTIRE 2022 Perceptual Image Quality Assessment Challenge track 1 Full-Reference.