Image Quality Assessment With Compressed Sampling
This work addresses a domain-specific issue in image processing by improving efficiency for high-resolution image quality assessment, though it appears incremental as it builds on existing NR-IQA methods with a focus on data reduction.
The paper tackles the problem of No-Reference Image Quality Assessment (NR-IQA) for high-resolution images, which often require resizing to fit model inputs, by proposing two networks (CL-IQA and CS-IQA) that use compressed sampling to reduce data usage while outperforming other methods on various datasets.
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.