Image Quality Assessment With Compressed Sampling

TL;DR

This paper introduces two novel no-reference image quality assessment networks that utilize compressed sampling and advanced feature extraction modules, achieving superior performance on high-resolution images with less data.

Contribution

The paper proposes two innovative NR-IQA networks incorporating compressed sampling and transformer-based modules, addressing input size limitations and improving accuracy.

Findings

Outperform existing methods on multiple datasets

Require less data for training and inference

Effective on high-resolution images

Abstract

No-Reference Image Quality Assessment (NR-IQA) aims at estimating image quality in accordance with subjective human perception. However, most methods focus on exploring increasingly complex networks to improve the final performance,accompanied by limitations on input images. Especially when applied to high-resolution (HR) images, these methods offen have to adjust the size of original image to meet model input.To further alleviate the aforementioned issue, we propose two networks for NR-IQA with Compressive Sampling (dubbed CL-IQA and CS-IQA). They consist of four components: (1) The Compressed Sampling Module (CSM) to sample the image (2)The Adaptive Embedding Module (AEM). The measurements are embedded by AEM to extract high-level features. (3) The Vision Transformer and Scale Swin TranBlocksformer Moudle(SSTM) to extract deep features. (4) The Dual Branch (DB) to get final quality score. Experiments show that our proposed methods outperform other methods on various datasets with less data usage.