No-reference image quality assessment (NR-IQA) quantifies image distortion. It plays an important role in computer vision. Distorted images vary greatly in content. Many existing methods tend to fuse content information with quality prediction. However, they often overlook human visual perception. To address this issue, we propose an attention-guided content-aware NR-IQA method. It combines meta-learning with image content understanding. The approach uses refined deep semantic features for quality evaluation. First, we train a meta-model on a baseline network. This improves sensitivity to diverse distortions. Second, we insert an attention module into the meta-model. This captures global information and highlights important regions. We also fuse multi-level semantic features. This enables a comprehensive description of both local and global distortions. Finally, we reduce feature dimensions and learn weights to predict the quality score. Extensive experiments show that our method achieves results closer to human perception. It effectively focuses on regions of interest during feature extraction.

1. [1] L. Zhou, C. Liu, A. Yadav, S. Azam, and A. Karim, “An image quality assessment method based on edge extraction and singular value for blurriness,” Machine Vision and Applications, Vol.35, No.3, Article No.37, 2024. https://doi.org/10.1007/s00138-024-01522-6
2. [2] J. Ryu, “A visual saliency-based neural network architecture for no-reference image quality assessment,” Applied Sciences, Vol.12, No.19, Article No.9567, 2022. https://doi.org/10.3390/app12199567
3. [3] S. Su, Q. Yan, Y. Zhu, C. Zhang, X. Ge, J. Sun, and Y. Zhang, “Blindly assess image quality in the wild guided by a self-adaptive hyper network,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 3664-3673, 2020. https://doi.org/10.1109/cvpr42600.2020.00372
4. [4] D. Li, T. Jiang, W. Lin, and M. Jiang, “Which has better visual quality: The clear blue sky or a blurry animal?,” IEEE Trans. on Multimedia, Vol.21, No.5, pp. 1221-1234, 2019. https://doi.org/10.1109/tmm.2018.2875354
5. [5] A. Mittal, A. K. Moorthy, and A. C. Bovik, “No-reference image quality assessment in the spatial domain,” IEEE Trans. on Image Processing, Vol.21, No.12, pp. 4695-4708, 2012. https://doi.org/10.1109/tip.2012.2214050
6. [6] J. Xu, P. Ye, Q. Li, H. Du, Y. Liu, and D. Doermann, “Blind image quality assessment based on high order statistics aggregation,” IEEE Trans. on Image Processing, Vol.25, No.9, pp. 4444-4457, 2016. https://doi.org/10.1109/tip.2016.2585880
7. [7] J. Kim and S. Lee, “Fully deep blind image quality predictor,” IEEE J. of Selected Topics in Signal Processing, Vol.11, No.1, pp. 206-220, 2017. https://doi.org/10.1109/jstsp.2016.2639328
8. [8] J. Wu, J. Ma, F. Liang, W. Dong, G. Shi, and W. Lin, “End-to-end blind image quality prediction with cascaded deep neural network,” IEEE Trans. on Image Processing, Vol.29, pp. 7414-7426, 2020. https://doi.org/10.1109/tip.2020.3002478
9. [9] W. Zhang, K. Ma, J. Yan, D. Deng, and Z. Wang, “Blind image quality assessment using a deep bilinear convolutional neural network,” IEEE Trans. on Circuits and Systems for Video Technology, Vol.30, No.1, pp. 36-47, 2020. https://doi.org/10.1109/tcsvt.2018.2886771
10. [10] H. Zhu, L. Li, J. Wu, W. Dong, and G. Shi, “MetaIQA: Deep meta-learning for no-reference image quality assessment,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 14131-14140, 2020. https://doi.org/10.1109/cvpr42600.2020.01415
11. [11] H. Zhu, L. Li, J. Wu, W. Dong, and G. Shi, “Generalizable no-reference image quality assessment via deep meta-learning,” IEEE Trans. on Circuits and Systems for Video Technology, Vol.32, No.3, pp. 1048-1060, 2022. https://doi.org/10.1109/tcsvt.2021.3073410
12. [12] N. Ponomarenko, L. Jin, O. Ieremeiev, V. Lukin, K. Egiazarian, J. Astola, B. Vozel, K. Chehdi, M. Carli, F. Battisti, and C.-C. J. Kuo, “Image database tid2013: Peculiarities, results and perspectives,” Signal Processing: Image Communication, Vol.30, pp. 57-77, 2015. https://doi.org/10.1016/j.image.2014.10.009
13. [13] H. Lin, V. Hosu, and D. Saupe, “KADID-10k: A large-scale artificially distorted iqa database,” 2019 Eleventh Int. Conf. on Quality of Multimedia Experience (QoMEX), 2019. https://doi.org/10.1109/qomex.2019.8743252
14. [14] H. Sheikh, M. Sabir, and A. Bovik, “A statistical evaluation of recent full reference image quality assessment algorithms,” IEEE Trans. on Image Processing, Vol.15, No.11, pp. 3440-3451, 2006. https://doi.org/10.1109/tip.2006.881959
15. [15] D. M. Chandler, “Most apparent distortion: Full-reference image quality assessment and the role of strategy,” J. of Electronic Imaging, Vol.19, No.1, Article No.011006, 2010. https://doi.org/10.1117/1.3267105
16. [16] D. Ghadiyaram and A. C. Bovik, “Massive online crowdsourced study of subjective and objective picture quality,” IEEE Trans. on Image Processing, Vol.25, No.1, pp. 372-387, 2016. https://doi.org/10.1109/tip.2015.2500021
17. [17] V. Hosu, H. Lin, T. Sziranyi, and D. Saupe, “KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment,” IEEE Trans. on Image Processing, Vol.29, pp. 4041-4056, 2020. https://doi.org/10.1109/tip.2020.2967829
18. [18] L. Zhang, L. Zhang, and A. C. Bovik, “A feature-enriched completely blind image quality evaluator,” IEEE Trans. on Image Processing, Vol.24, No.8, pp. 2579-2591, 2015. https://doi.org/10.1109/tip.2015.2426416
19. [19] S. Bosse, D. Maniry, K.-R. Muller, T. Wiegand, and W. Samek, “Deep neural networks for no-reference and full-reference image quality assessment,” IEEE Trans. on Image Processing, Vol.27, No.1, pp. 206-219, 2018. https://doi.org/10.1109/tip.2017.2760518