Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment
This work addresses the problem of no-reference quality assessment for super-resolution images, providing a more reliable metric for researchers and practitioners, though it is incremental as it builds on existing perceptual quality assessment approaches.
The paper tackles the challenge of evaluating super-resolution image quality by proposing TPNet, a dual-stream network that jointly learns textural and perceptual information, which achieves more accurate visual quality scores and better alignment with human judgment than existing methods.
Image super-resolution (SR) has been widely investigated in recent years. However, it is challenging to fairly estimate the performance of various SR methods, as the lack of reliable and accurate criteria for the perceptual quality. Existing metrics concentrate on the specific kind of degradation without distinguishing the visual sensitive areas, which have no ability to describe the diverse SR degeneration situations in both low-level textural and high-level perceptual information. In this paper, we focus on the textural and perceptual degradation of SR images, and design a dual stream network to jointly explore the textural and perceptual information for quality assessment, dubbed TPNet. By mimicking the human vision system (HVS) that pays more attention to the significant image areas, we develop the spatial attention to make the visual sensitive information more distinguishable and utilize feature normalization (F-Norm) to boost the network representation. Experimental results show the TPNet predicts the visual quality score more accurate than other methods and demonstrates better consistency with the human's perspective. The source code will be available at \url{http://github.com/yuqing-liu-dut/NRIQA_SR}