Abstract
Achieving subjective and objective quality assessment of underwater images is of high significance in underwater visual perception and image/video processing. However, the development of underwater image quality assessment (UIQA) is limited for the lack of publicly available underwater image datasets with human subjective scores and reliable objective UIQA metrics. To address this issue, we establish a large-scale underwater image dataset, dubbed UID2021, for evaluating no-reference (NR) UIQA metrics. The constructed dataset contains 60 multiply degraded underwater images collected from various sources, covering six common underwater scenes (i.e., bluish scene, blue-green scene, greenish scene, hazy scene, low-light scene, and turbid scene), and their corresponding 900 quality improved versions are generated by employing 15 state-of-the-art underwater image enhancement and restoration algorithms. Mean opinion scores with 52 observers for each image of UID2021 are also obtained by using the pairwise comparison sorting method. Both in-air and underwater-specific NR IQA algorithms are tested on our constructed dataset to fairly compare their performance and analyze their strengths and weaknesses. Our proposed UID2021 dataset enables ones to evaluate NR UIQA algorithms comprehensively and paves the way for further research on UIQA. The dataset is available at https://github.com/Hou-Guojia/UID2021.
- [1] . 2019. An in-depth survey of underwater image enhancement and restoration. IEEE Access 7 (Aug. 2019), 123638–123657.Google Scholar
Cross Ref
- [2] . 2020. A review on intelligence dehazing and color restoration for underwater images. IEEE Trans. Syst. Man Cybern. Syst. 50, 5 (May 2020), 1820–1832.Google Scholar
Cross Ref
- [3] . 2020. Diving deeper into underwater image enhancement: A survey. Signal Process. Image Commun. 89 (Nov. 2020), 115978.Google Scholar
Cross Ref
- [4] . 2015. An underwater color image quality evaluation metric. IEEE Trans. Image Process. 24, 12 (Dec. 2015), 6062–6071.Google Scholar
Digital Library
- [5] . 2016. Human-visual-system-inspired underwater image quality measures. IEEE J. Ocean. Eng. 41, 3 (July 2016), 541–551.Google Scholar
Cross Ref
- [6] . 2017. An imaging-inspired no-reference underwater color image quality assessment metric. Comput. Electron. Eng. 70 (Dec. 2017), 904–913.Google Scholar
Cross Ref
- [7] . 2021. A reference-free underwater image quality assessment metric in frequency domain. Signal Process. Image Commun. 94 (March 2021), 116218.Google Scholar
Cross Ref
- [8] . 2019. An underwater image enhancement benchmark dataset and beyond. IEEE Trans. Image Process. 29 (Nov. 2019), 4376–4389.Google Scholar
Cross Ref
- [9] . 2020. Real-world underwater enhancement: Challenges, benchmarks, and solutions under natural light. IEEE Trans. Circuits Syst. Video Technol. 30, 12 (Jan. 2020), 4861–4875.Google Scholar
Digital Library
- [10] . 2021. Underwater single image color restoration using haze-lines and a new quantitative dataset. IEEE Trans. Pattern Anal. Mach. Intell. 43, 8 (Aug. 2021), 2822–2837.Google Scholar
- [11] . 2016. A dataset to evaluate underwater image restoration methods. In Proceedings of the 2016 MTS/IEEE OCEANS Conference (OCEANS’16). 1–6.Google Scholar
Cross Ref
- [12] . 2019. Bio-inspired optimization algorithms for real underwater image restoration. Signal Process. Image Commun. 77 (Sept. 2019), 49–65.Google Scholar
Digital Library
- [13] . 2020. Underwater scene prior inspired deep underwater image and video enhancement. Pattern Recognit. 98 (Feb. 2020), 107038.Google Scholar
Digital Library
- [14] . 2020. Benchmarking underwater image enhancement and restoration, and beyond. IEEE Access 8 (July 2020), 122078–122091.Google Scholar
Cross Ref
- [15] . 2020. Underwater no-reference image quality assessment for display module of ROV. Sci. Program. 2 (Aug. 2020), 1–15.Google Scholar
- [16] . 2021. Underwater image quality assessment: Subjective and objective methods. IEEE Trans. Multimedia 24 (April 2021), 1980–1989.Google Scholar
Cross Ref
- [17] . 2006. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans. Image Process. 15, 11 (Nov. 2006), 3440–3451.Google Scholar
Digital Library
- [18] . 2023. MICT Image Quality Evaluation Database. Retrieved January 10, 2023 from https://computervisiononline.com/dataset/1105138668.Google Scholar
- [19] . 2009. TID2008: A database for evaluation of full-reference visual quality assessment metrics. Adv. Modern Radioelectron. 10, 4 (2009), 30–45.Google Scholar
- [20] . 2015. CID2013: A database for evaluating no-reference image quality assessment algorithms. IEEE Trans. Image Process. 24, 1 (Jan. 2015), 390–402.Google Scholar
Cross Ref
- [21] . 2017. MDID: A multiply distorted image database for image quality assessment. Pattern Recognit. 61 (Jan. 2017), 153–168.Google Scholar
Digital Library
- [22] . 2017. Waterloo exploration database: New challenges for image quality assessment models. IEEE Trans. Image Process. 26, 2 (Feb. 2017), 1004–1016.Google Scholar
Digital Library
- [23] . 2012. Objective quality assessment of multiply distorted images. In Proceedings of the 2012 Conference Record of the 46th Asilomar Conference on Signals, Systems, and Computers (ASILOMAR’12). 1693–1697.Google Scholar
Cross Ref
- [24] 2015. Image database TID2013: Peculiarities, results and perspectives. Signal Process. Image Commun. 30 (Jan. 2015), 57–77.Google Scholar
Digital Library
- [25] . 2017. A multidistortion database for image quality. In Proceedings of the International Workshop on Computational Color Imaging (CCIW’17). 95–104. http://www.mmsp.unimib.it/image-quality/.Google Scholar
Cross Ref
- [26] . 2011. No-reference blur assessment of digital pictures based on multifeature classifiers. IEEE Trans. Image Process. 20, 1 (Jan. 2011), 64–75.Google Scholar
Digital Library
- [27] . 2016. Massive online crowdsourced study of subjective and objective picture quality. IEEE Trans. Image Process. 25, 1 (Jan. 2016), 372–387.Google Scholar
Digital Library
- [28] . 2018. KonIQ-10k: Towards an ecologically valid and large-scale IQA database. arXiv:1803.08489.Google Scholar
- [29] . 2006. Pseudo no reference image quality metric using perceptual data hiding. In Proceedings of SPIE Human Vision and Electronic Imaging.Google Scholar
Cross Ref
- [30] . 2010. Most apparent distortion: Full-reference image quality assessment and the role of strategy. J. Electron. Imag. 19, 1 (Jan. 2010), 011006.Google Scholar
Cross Ref
- [31] . 2015. Achieving turbidity robustness on underwater images local feature detection. Int. J. Comput. Vis. 60, 2 (Sept. 2015), 91–110.Google Scholar
- [32] . 2018. A new database for evaluating underwater image processing methods. In Proceedings of the 2018 8th International Conference on Image Processing Theory, Tools, and Applications (IPTA’18). 1–6.Google Scholar
Cross Ref
- [33] . 2010. A two-step framework for constructing blind image quality indices. IEEE Signal Process. Lett. 17, 5 (May 2010), 513–516.Google Scholar
Cross Ref
- [34] . 2012. No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21, 12 (Dec. 2012), 4695–4708.Google Scholar
Digital Library
- [35] . 2013. Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20, 3 (March 2013), 209–212.Google Scholar
Cross Ref
- [36] . 2012. Blind image quality assessment: A natural scene statistics approach in the DCT domain. IEEE Trans. Image Process. 21, 8 (Aug. 2012), 3339-3352.Google Scholar
Digital Library
- [37] . 2018. End-to-end blind image quality assessment using deep neural networks. IEEE Trans. Image Process. 27, 3 (March 2018), 1202–1213.Google Scholar
Cross Ref
- [38] . 2020. MetaIQA: Deep meta-learning for no-reference image quality assessment. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). 14131–14140.Google Scholar
Cross Ref
- [39] . 2020. End-to-end blind image quality prediction with cascaded deep neural network. IEEE Trans. Image Process. 29 (June 2020), 7414–7426.Google Scholar
Digital Library
- [40] . 2014. Convolutional neural networks for no-reference image quality assessment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’14). 1733–1740.Google Scholar
Digital Library
- [41] . 2020. Blindly assess image quality in the wild guided by a self-adaptive hyper network. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). 3664–3673.Google Scholar
Cross Ref
- [42] . 2020. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Trans. Circuits Syst. Video Technol. 30, 1 (Jan. 2020), 36–47.Google Scholar
Cross Ref
- [43] . 2018. Deep neural networks for no-reference and full-reference image quality assessment. IEEE Trans. Image Process. 27, 1 (Jan. 2018), 206–219.Google Scholar
Cross Ref
- [44] . 2021. Uncertainty-aware blind image quality assessment in the laboratory and wild. IEEE Trans. Image Process. 30 (2021), 3474–3486.Google Scholar
Digital Library
- [45] . 2022. Continual learning for blind image quality assessment. IEEE Trans. Pattern Anal. Mach. Intell. Early access, 2022.Google Scholar
- [46] . 2022. MSTRIQ: No reference image quality assessment based on swin transformer with multi-stage fusion. In Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’22). 1268–1277.Google Scholar
Cross Ref
- [47] . 2019. A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB). IEEE Trans. Image Process. 18, 4 (April 2009), 717–728.Google Scholar
Digital Library
- [48] . 2011. A no-reference image blur metric based on the cumulative probability of blur detection (CPBD). IEEE Trans. Image Process. 20, 9 (Sept. 2011), 2678–2683.Google Scholar
Digital Library
- [49] . 2016. No-reference image blur assessment based on discrete orthogonal moments. IEEE Trans. Image Cybern. 46, 1 (Jan. 2016), 39–50.Google Scholar
Cross Ref
- [50] . 2015. Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans. Image Process. 24, 11 (Nov. 2015), 3888–3901.Google Scholar
Digital Library
- [51] . 2019. Pre-attention and spatial dependency driven no-reference image quality assessment. IEEE Trans. Multimedia 21, 9 (Sept. 2019), 2305–2318.Google Scholar
- [52] . 2021. Precise no-reference image quality evaluation based on distortion identification. ACM Trans. Multimed. Comput. Commun. Appl. 17, 110 (Oct. 2021), 1–21.Google Scholar
Digital Library
- [53] . 2022. UIF: An objective quality assessment for underwater image enhancement. IEEE Trans. Image Process. 31 (2022), 5456–5468.Google Scholar
Digital Library
- [54] . 2022. Underwater image enhancement quality evaluation: Benchmark dataset and objective metric. IEEE Trans. Circuits Syst. Video Technol. 32, 9 (Sept. 2022), 5959–5974.Google Scholar
Cross Ref
- [55] . 2022. Twice Mixing: A rank learning based quality assessment approach for underwater image enhancement. Signal Process. Image Commun. 102 (March 2022), 116622.Google Scholar
Digital Library
- [56] . 2022. Underwater Ranker: Learn which is better and how to be better. arXiv:2208.06857.Google Scholar
- [57] . 2015. Automatic red channel underwater image restoration. J. Vis. Commun. Image Represent. 26 (Jan. 2015), 132–145.Google Scholar
Digital Library
- [58] . 2019. An efficient nonlocal variational method with application to underwater image restoration. Neurocomputing 369 (Dec. 2019), 106–121.Google Scholar
Digital Library
- [59] . 2016. Underwater image enhancement by dehazing with minimum information loss and histogram distribution prior. IEEE Trans. Image Process. 25, 12 (Dec. 2016), 5664–5677.Google Scholar
Digital Library
- [60] . 2020. A hybrid framework for underwater image enhancement. IEEE Access 8 (Oct. 2020), 2169–3536.Google Scholar
- [61] . 2022. Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE Trans. Image Process. 31 (June 2022), 3997–4010.Google Scholar
Digital Library
- [62] . 2018. Color balance and fusion for underwater image enhancement. IEEE Trans. Image Process. 27, 1 (Jan. 2018), 379–393.Google Scholar
Cross Ref
- [63] . n.d. Bubble Vision Underwater Imaging. Retrieved January 10, 2023 from https://bubblevision.com.Google Scholar
- [64] . 2021. Bayesian retinex underwater image enhancement. Eng. Appl. Artif. Intell. 101 (May 2021), 104171.Google Scholar
Cross Ref
- [65] . 2007. Underwater image enhancement using an integrated colour model. IAENG Int. J. Comput. Sci. 34, 2 (March 2007), 239–244.Google Scholar
- [66] . 2020. Underwater image enhancement with global–local networks and compressed-histogram equalization. Signal Process. Image Commun. 86 (Aug. 2020), 115892.Google Scholar
Cross Ref
- [67] . 2018. Hue preserving-based approach for underwater colour image enhancement. IET Image Process. 12, 2 (Feb. 2018), 292–298.Google Scholar
Cross Ref
- [68] . 2017. Underwater image restoration based on image blurriness and light absorption. IEEE Trans. Image Process. 26, 4 (April 2017), 1579–1594.Google Scholar
Digital Library
- [69] . 2020. L2UWE: A framework for the efficient enhancement of low-light underwater images using local contrast and multi-scale fusion. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’20). 538–539.Google Scholar
Cross Ref
- [70] . 2017. Two-step approach for single underwater image enhancement. In Proceedings of the 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS’17). 789–794.Google Scholar
Cross Ref
- [71] . 2021. Underwater image enhancement via medium transmission-guided multi-color space embedding. IEEE Trans. Image Process. 30 (May 2021), 4985–5000.Google Scholar
Cross Ref
- [72] . 2022. A variational framework for underwater image dehazing and deblurring. IEEE Trans. Circuits Syst. Video Technol. 32, 6 (June 2022), 3514–3526.Google Scholar
Cross Ref
- [73] . 2020. A novel dark channel prior guided variational framework for underwater image restoration. J. Vis. Commun. Image Represent. 66 (Jan. 2020), 102732.Google Scholar
Digital Library
- [74] . 2014. A retinex-based enhancing approach for single underwater image. In Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP’14). 4572–4576.Google Scholar
Cross Ref
- [75] . 2012. Analysis of public image and video databases for quality assessment. IEEE J. Sel. Top. Signal. Process. 6, 6 (Aug. 2012), 616–625.Google Scholar
Cross Ref
- [76] . 2021. Leveraging deep statistics for underwater image enhancement. ACM Trans. Multimed. Comput. Commun. Appl. 17, 116 (Oct. 2021), 1–20.Google Scholar
Digital Library
- [77] . 2022. Enhancing underwater image via adaptive color and contrast enhancement, and denoising. Eng. Appl. Artif. Intell. 111 (May 2022), 104759.Google Scholar
Cross Ref
- [78] . 2022. SGUIE-Net: Semantic attention guided underwater image enhancement with multi-scale perception. IEEE Trans. Image Process. 31 (Oct. 2022), 6816–6830.Google Scholar
Digital Library
- [79] . 2022. Underwater image enhancement with hyper-Laplacian reflectance priors. IEEE Trans. Image Process. 31 (Aug. 2022), 5442–5455.Google Scholar
Digital Library
- [80] . 2022. Underwater image restoration via backscatter pixel prior and color compensation. Eng. Appl. Artif. Intell. 111 (May 2022), 104785.Google Scholar
Cross Ref
- [81] . 2022. TEBCF: Real-world underwater image texture enhancement model based on blurriness and color fusion. IEEE Trans. Geosci. Remote Sens. 60 (Oct. 2021), 4204315.Google Scholar
Cross Ref
- [82] . 2022. Beyond single reference for training: Underwater image enhancement via comparative learning. IEEE Trans. Circuits Syst. Video Technol. Early access, November 28, 2022.Google Scholar
Cross Ref
- [83] . 2022. Single underwater image enhancement using integrated variational model, Digit. Signal Process. 129 (2022), 103660.Google Scholar
Digital Library
- [84] . 2022. No-reference image quality assessment via transformers, relative ranking, and self-consistency. In Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV’22). 3989–3999.Google Scholar
Cross Ref
Index Terms
UID2021: An Underwater Image Dataset for Evaluation of No-Reference Quality Assessment Metrics
Recommendations
An Underwater Color Image Quality Evaluation Metric
Quality evaluation of underwater images is a key goal of underwater video image retrieval and intelligent processing. To date, no metric has been proposed for underwater color image quality evaluation (UCIQE). The special absorption and scattering ...
A Training-Based Blind Underwater Image Quality Evaluation Metric
ICBDT '22: Proceedings of the 5th International Conference on Big Data TechnologiesDue to the unique image formation principle and the limitations of imaging devices, underwater images usually suffer from low contrast, color degradation, and blurring effects, which seriously hinder the interpretation of the image content. Additionally,...
A critical survey of state-of-the-art image inpainting quality assessment metrics
We present a thorough overview of image inpainting quality assessment (IIQA) metrics.We introduce a new framework for clustering IIQA metrics into major groups.We provide a comprehensive performance analysis of IIQA metrics on public databases.We ...






Comments