Color Balance and Fusion for Underwater Image Enhancement
Open accessThe DOI matches its Crossref record; 75 of the 76 references it cites were found in a registry or an index.
Abstract
We introduce an effective technique to enhance the images captured underwater and degraded due to the medium scattering and absorption. Our method is a single image approach that does not require specialized hardware or knowledge about the underwater conditions or scene structure. It builds on the blending of two images that are directly derived from a color-compensated and white-balanced version of the original degraded image. The two images to fusion, as well as their associated weight maps, are defined to promote the transfer of edges and color contrast to the output image. To avoid that the sharp weight map transitions create artifacts in the low frequency components of the reconstructed image, we also adapt a multiscale fusion strategy. Our extensive qualitative and quantitative evaluation reveals that our enhanced images and videos are characterized by better exposedness of the dark regions, improved global contrast, and edges sharpness. Our validation also proves that our algorithm is reasonably independent of the camera settings, and improves the accuracy of several image processing applications, such as image segmentation and keypoint matching.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“However, these algorithms do not consider the spatial variance of the degradation over the field of view [3,4,5,6].”
From Underwater Optical-Sonar Image Fusion Systems (2022) · cites this paper as [5]
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 1×
“Additionally, our assessment considers the index Qu [63] that combines the benefits of SSIM index [70] and Euclidean color distance.”
MethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Single image haze removal using dark channel prior
He, K., Sun, J., & Tang, X. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.168 · Cited by 7,601 · cited 3×
“Recently, several algorithms that specifically restore underwater images based on Dark Channel Prior (DCP) [19], [26] have been introduced.”
BackgroundMethodThe Laplacian pyramid as a compact image code
Burt, P., & Adelson, E. (1983) · IEEE Transactions on Communications · doi:10.1109/tcom.1983.1095851 · Cited by 6,077 · cited 4×
“Following the traditional multi-scale fusion strategy [55], each source input Ik is decomposed into a Laplacian pyramid [57] while the normalized weight maps W̄k are decomposed using a Gaussian pyramid.”
BackgroundMethodInfluentialFrequency-tuned salient region detection
Achanta, R., Hemami, S., Estrada, F., & Susstrunk, S. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206596 · Cited by 4,167
Single image super-resolution from transformed self-exemplars
Huang, J.-B., Singh, A., & Ahuja, N. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299156 · Cited by 3,472 · cited 1×
“This extension is presented in [33] and builds on superresolution from transformed self-exemplars [34] to derive two high-resolution (HR) images, respectively from the output derived in [31] and from a denoised/descattered version of”
MethodThe Retinex Theory of Color Vision
Land, E. H. (1977) · Scientific American · doi:10.1038/scientificamerican1277-108 · Cited by 2,981 · cited 6×
“On this set of images, we applied the following methods: the classical white-patch max RGB algorithm [42], the Gray-World [43], but also the more recent Shades-of-Grey [41] and Gray-Edge [40].”
MethodInfluentialGomarasca, M. A. (2009) · Basics of Geomatics · doi:10.1007/978-1-4020-9014-1_8 · Cited by 2,614
Single image haze removal using dark channel prior
He, K., Sun, J., & Tang, X. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206515 · Cited by 2,414
Sharma, G., Wu, W., & Dalal, E. N. (2005) · Color Research & Application · doi:10.1002/col.20070 · Cited by 2,175 · cited 1×
“A more complex, yet more accurate, color difference measure, which solves the perceptual uniformity issue of CIE76 and CIE94, is CIEDE2000 [68], [69].”
Background
Research works printed but not linked: 1
- ebner, 2007, Color Constancy
Cited by
Items 101–200 of 1,000
Underwater Image Enhancement With Cascaded Contrastive Learning
Liu, Y., Jiang, Q., Wang, X., Luo, T., & Zhou, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521739 · Cited by 88
“The three traditional methods are Fusion [51], SMBL [52], and MLLE [53].”
Application of computer vision in fish intelligent feeding system—A review
An, D. U., Jin, H., Wei, Y., Wang, Y., & Yu, X. (2020) · Aquaculture Research · doi:10.1111/are.14907 · Cited by 95
Augmented weighted bidirectional feature pyramid network for marine object detection
Gao, J., Xu, G., Zhang, Y., Wang, R., & Shao, K. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121688 · Cited by 90
Shi, Z., Feng, Y., Zhao, M., Zhang, E., & He, L. (2019) · IEEE Access · doi:10.1109/access.2019.2936444 · Cited by 87
“The purpose of using the Gamma function in our work is similar to that in Ancuti’s work [35].”
MethodSingle Underwater Image Restoration by Contrastive Learning
Han, J., Shoeiby, M., Malthus, T., Botha, E., Anstee, J. M., Anwar, S., Wei, R., Petersson, L., & Armin, M. A. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9553857 · Cited by 88
“Input CUT [10] CycleGAN [11] UWCNN [3] Retinex [12] Fusion [13] DCP [6] IBLA [8] CWR (ours) Reference”
BackgroundMethodThe Retinex based improved underwater image enhancement
Hassan, N., Ullah, S., Bhatti, N., Mahmood, H., & Zia, M. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09752-2 · Cited by 83
“Ancuti et al. attempt to enhance the underwater image affected by physical properties of the medium (water) [1].”
BackgroundMulti-Input Dual-Stream Capsule Network for Improved Lung and Colon Cancer Classification
Ali, M., & Ali, R. (2021) · Diagnostics · doi:10.3390/diagnostics11081485 · Cited by 85
“In this paper, we adopt a color balancing technique for digital images which was introduced in [56], where the authors try to compensate the red and green channels of the underwater images.”
BackgroundMethodMulticolor Light Attenuation Modeling for Underwater Image Restoration
Zhou, J., Wang, Y., Li, C., & Zhang, W. (2023) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2023.3275615 · Cited by 89
“Traditional model-free methods (e.g., histogram equalization [6] and white balance [7]) can improve contrast and remove color degradation.”
MethodGuo, X., Chen, X., Wang, S., & Pun, C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3525593 · Cited by 100
“Multiscale fusion strategies have been employed by Ancuti et al. [42] and Kang et al. [43] to blend images from color-compensated and white-balanced versions, enhancing global contrast and edge sharpness.”
A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning
Cong, X., Zhao, Y., Gui, J., Hou, J., & Tao, D. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3668671 · Cited by 89
“U NDERWATER imaging is an important task in the field of computer vision [6], [136].”
Deep Color Compensation for Generalized Underwater Image Enhancement
Rao, Y., Liu, W., Li, K., Fan, H., Wang, S., & Dong, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3305777 · Cited by 88
“To further promote the performance, Ancuti et al. [27] developed a white-balance-based multi-scale fusion strategy to make full use of the saliency and saturation information encapsulated in the degraded image.”
BackgroundYang, M., Sowmya, A., Wei, Z., & Zheng, B. (2019) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2018.2886093 · Cited by 83
“They proposed an improved white balance by red channel loss compensation before resorting to the conventional Gray-World [13].”
MethodLiu, X., Gao, Z. Y., & Chen, B. M. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.07.130 · Cited by 81
“The original input images contain intense green hue, and EUF [37], UVE [11], WCID [9], however, fails to remove the color shift.”
BackgroundMethodInfluentialUnderwater Image Restoration Based on a Parallel Convolutional Neural Network
Wang, K., Hu, Y., Chen, J., Wu, X., Zhao, X. B., & Li, Y. (2019) · Remote Sensing · doi:10.3390/rs11131591 · Cited by 77
“…methods, such as histogram equalization [9], white balance [10], pixel stretching [11,12], retinex-based methods [13,14] and fusion-based methods [15–17], generally improve image visual effect by modifying image pixels without concerning the physical degradation mechanism of underwater images.”
MethodFW-GAN: Underwater image enhancement using generative adversarial network with multi-scale fusion
Wu, J., Liu, X., Lu, Q., Lin, Z., Qin, N., & Shi, Q. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116855 · Cited by 81
Underwater image enhancement by combining color constancy and dehazing based on depth estimation
Muniraj, M., & Vaithiyanathan, D. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.003 · Cited by 76
MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility
Bakht, A. B., Jia, Z., Din, M. U., Akram, W., Saoud, L. S., Seneviratne, L. D., Lin, D., He, S., & Hussain, I. (2024) · Ecological Informatics · doi:10.1016/j.ecoinf.2024.102631 · Cited by 82
UW-CycleGAN: Model-Driven CycleGAN for Underwater Image Restoration
Yan, H., Zhang, Z., Xu, J., Wang, T., An, P., Wang, A., & Duan, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3315772 · Cited by 92
Nguyen, H.-T., Lee, E.-H., & Lee, S. (2019) · Sensors · doi:10.3390/s20010094 · Cited by 71
“An example picture of poor visibility in turbid water [11].”
BackgroundDewaterNet: A fusion adversarial real underwater image enhancement network
Li, H., & Zhuang, P. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116248 · Cited by 77
Underwater image enhancement using adaptive color restoration and dehazing
Li, T., Rong, S., Zhao, W., Chen, L., Liu, Y., Zhou, H., & He, B. (2022) · Optics Express · doi:10.1364/oe.449930 · Cited by 71
Ji, W., Peng, J., Xu, B., & Zhang, T. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107522 · Cited by 74
Deep Color-Corrected Multiscale Retinex Network for Underwater Image Enhancement
Qi, H., Zhou, H., Dong, J., & Dong, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3338611 · Cited by 91
“Inspired by the success of the fusion-based method [40], Li et al. [27] proposed the WaterNet, which was used to learn fusion weights for fusing different enhancement results.”
MethodInfluentialXue, X., Li, Z., Ma, L., Jia, Q., Liu, R., & Fan, X. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109041 · Cited by 76
TAFormer: A Transmission-Aware Transformer for Underwater Image Enhancement
Li, Y., Mi, Z., Wang, Y., Jiang, S., & Fu, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3455353 · Cited by 78
“For example, Ancuti et al. successively proposed different multi-scale fusion methods for enhancing underwater images, such as the fusion-based method [10].”
Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion
Tang, Q., Yang, J., He, X., Jia, W., Zhang, Q., & Liu, H. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.103086 · Cited by 76
Classical and state-of-the-art approaches for underwater image defogging: a comprehensive survey
Zhou, J., Zhang, D., & Zhang, W. (2020) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2000190 · Cited by 68
Deep learning-based visual detection of marine organisms: A survey
Wang, N., Chen, T., Liu, S., Wang, R., Karimi, H. R., & Lin, Y. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.018 · Cited by 69
Underwater image quality optimization: Researches, challenges, and future trends
Wang, M., Zhang, K., Wei, H., Chen, W., & Zhao, T. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.104995 · Cited by 76
Song, H., Chang, L., Chen, Z., & Ren, P. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3097804 · Cited by 71
“In our experiment, the corresponding points are detected and matched using SIFT [31], the outliers are removed with RANSAC [39] and the datasets of images are acquired from [25], [40], [41].”
BackgroundMethodChen, R., Cai, Z., & Cao, W. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3134762 · Cited by 77
“Here, the enhancement results of the proposed method are compared with some state-of-the-art models, i.e., fusion-based [17], UDCP [11], red channel [12], retinex-based [18], FUIE [23], UICEˆ2-Net [25], and GLCHE [26].”
MethodLiu, X.-W., Pedersen, M., & Wang, R.-F. (2022) · Digit. Signal Process. · doi:10.1016/j.dsp.2022.103547 · Cited by 52
UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots
Yu, B., Wu, J., & Islam, M. J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161471 · Cited by 100
“However, these parameters are not always known; in fact, they are estimated by using noisy depth priors for image enhancement and color correction [5, 65].”
BackgroundHybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration
Yan, S., Chen, X., Wu, Z., Tan, M. H., & Yu, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3309408 · Cited by 75
“processing methods [5], [6], [7], [8], [9] or deep learning”
BackgroundMethodCBLA: Color-Balanced Locally Adjustable Underwater Image Enhancement
Jha, M., & Bhandari, A. K. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3396850 · Cited by 68
“Fusion-based methods were deployed by Ancuti et al. [30] to enhance images based on white-balancing models by fusing the color and contrast-enhanced models.”
MethodLi, K., Fan, H., Qi, Q., Yan, C., Sun, K., & Wu, Q. M. J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3328272 · Cited by 67
“…physical model-free methods typically directly modify the pixel values or distribution to improve the visual quality, such as histogram equalization [17], [18], white balance [19], fusion based approaches [20], variational frameworks [21], [22], [23], and Retinex-based algorithms [24], [25], [26].”
MethodSingle underwater image restoration by decomposing curves of attenuating color
Dai, C., Lin, M., Wu, X., Wang, Z., & Guan, Z. (2019) · Optics & Laser Technology · doi:10.1016/j.optlastec.2019.105947 · Cited by 70
Underwater Image Enhancement via Physical-Feedback Adversarial Transfer Learning
Zhou, Y., Yan, K., & Li, X. (2021) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2021.3104055 · Cited by 65
UMGAN: Underwater Image Enhancement Network for Unpaired Image-to-Image Translation
Sun, B., Mei, Y., Yan, N., & Chen, Y. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11020447 · Cited by 65
Guidelines for Underwater Image Enhancement Based on Benchmarking of Different Methods
Mangeruga, M., Bruno, F., Cozza, M., Agrafiotis, P., & Skarlatos, D. P. (2018) · Remote Sensing · doi:10.3390/rs10101652 · Cited by 69
“, in [31], as well as in [32], where an updated version of the method is presented, delivered a novel strategy to enhance underwater videos and images built on the fusion principles.”
MethodAn efficient nonlocal variational method with application to underwater image restoration
Hou, G., Pan, Z., Wang, G., Yang, H., & Duan, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.08.041 · Cited by 68
Li, C., Tang, S., Kwan, H. K., Yan, J., & Zhou, T. (2020) · IEEE Access · doi:10.1109/access.2020.3019354 · Cited by 70
“Ancuti et al. [11] assumed that green channel is the counterpart of red channel, and they compensate the attenuation of red channel and blue channel from that of the green channel.”
BackgroundMulti-scale retinex-based adaptive gray-scale transformation method for underwater image enhancement
Zhou, J., Yao, J., Zhang, W., & Zhang, D. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11327-8 · Cited by 68
Mutual Retinex: Combining Transformer and CNN for Image Enhancement
Jiang, K., Wang, Q., An, Z., Wang, Z., Zhang, C., & Lin, C. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3369321 · Cited by 67
“Following [36], we adopt the Macbeth Color Checker as the ground truth, and measure the perceptual distances between the color patches from Macbeth Color Checker and the enhanced results using the CIEDE2000 formula.”
MethodInfluentialHuo, F., Li, B., & Zhu, X. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00221 · Cited by 78
“Some researchers propose underwater image enhancement methods [7, 6, 15, 36, 31, 14] while ignore the influence of diverse water types.”
BackgroundMethodUnderwater Image Enhancement Based on Adaptive Color Correction and Improved Retinex Algorithm
Lin, S., Li, Z., Zheng, F., Zhao, Q., & Li, S. (2023) · IEEE Access · doi:10.1109/access.2023.3258698 · Cited by 66
“By the sharpen method proposed in [14], we strengthen the edge of the color corrected image I to get the sharpen image I S .”
BackgroundMethodInfluentialYi, D., Ahmedov, H. B., Jiang, S., Li, Y., Flinn, S. J., & Fernandes, P. G. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127488 · Cited by 68
Wang, Y., Yu, X., An, D. U., & Wei, Y. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106182 · Cited by 62
Generation-Based Joint Luminance-Chrominance Learning for Underwater Image Quality Assessment
Wang, Z., Shen, L., Wang, Z., Lin, Y., & Jin, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3212788 · Cited by 67
“2, raw images are enhanced by the representative UIE methods including: HP [7], IBLA [35], two-step [36], ACPAB [37], fusion-18 [40], FUNIE-GAN [39], UGAN [38], and Water-Net [15].”
BackgroundMethodInfluentialPolarization-Driven Solution for Mitigating Scattering and Uneven Illumination in Underwater Imagery
Shen, L., Reda, M., Zhang, X., Zhao, Y., & Kong, S. G. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3358828 · Cited by 94
“Ancuti et al. [39] applied multiscale fusion of images using color compensation and white balance versions directly derived from the original degraded image.”
BackgroundMethodZhang, D., Wu, C., Zhou, J., Zhang, W., Lin, Z., Polat, K., & Alenezi, F. S. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.11.008 · Cited by 63
Underwater image enhancement based on DCP and depth transmission map
Yu, H., Li, X., Lou, Q., Lei, C., & Liu, Z. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08701-3 · Cited by 59
Aguirre-Castro, O. A., García-Guerrero, E. E., López-Bonilla, O. R., Tlelo‐Cuautle, E., Lopez-Mancilla, D., Cárdenas-Valdez, J. R., Tiznado, J. E. O., & Inzunza-González, E. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.074 · Cited by 59
UIALN: Enhancement for Underwater Image With Artificial Light
Li, M., Wang, K., Shen, L., Lin, Y., Wang, Z., & Zhao, Q. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3237993 · Cited by 59
“Although the results of Fusion18 [44] and WaterNet [31] alleviate a certain degree of color distortion, the color cast and uneven brightness still exist.”
BackgroundResultInfluentialCascaded frameworks in underwater optical image restoration
Li, B., Chen, Z., Lu, L., Qi, P., Zhang, L., Ma, Q., Hu, H., Zhai, J., & Li, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102809 · Cited by 61
Underwater Image Enhancement Using Successive Color Correction and Superpixel Dark Channel Prior
Lee, H. S., Moon, S. W., & Eom, I. K. (2020) · Symmetry · doi:10.3390/sym12081220 · Cited by 63
“where IA(x) is the final balanced underwater image based on UWB method [10].”
MethodInfluentialSubsea Pipeline Corrosion Estimation by Restoring and Enhancing Degraded Underwater Images
Khan, A., Ali, S. S. A., Anwer, A., Adil, S. H., & Mériaudeau, F. (2018) · IEEE Access · doi:10.1109/access.2018.2855725 · Cited by 61
“[31], [55], and [59] have investigated underwater image enhancement using different techniques.”
InfluentialAttenuation Coefficient Guided Two-Stage Network for Underwater Image Restoration
Lin, Y., Shen, L., Wang, Z., Wang, K., & Zhang, X. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3048619 · Cited by 58
“Model-free approaches [1]–[3] restore the underwater image by adjusting the pixel values of the image, without considering the underwater physical distortion process.”
Sand-Dust Image Enhancement Using Successive Color Balance With Coincident Chromatic Histogram
Park, T. H., & Eom, I. K. (2021) · IEEE Access · doi:10.1109/access.2021.3054899 · Cited by 63
“If κ is set to 1, δ ( x ) is the same as that in the conventional underwater image color correction [29].”
BackgroundMethodInfluentialTwice Mixing: A rank learning based quality assessment approach for underwater image enhancement
Fu, Z., Fu, X., Huang, Y., & Ding, X. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116622 · Cited by 62
Underwater image enhancement via frequency and spatial domains fusion
Zhang, W., Li, X., Huang, Y., Xu, S., Tang, J., & Hu, H. (2025) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2025.108826 · Cited by 60
Ma, H., Huang, J., Shen, C., & Jiang, Z. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111411 · Cited by 56
Zhang, D., He, Z., Zhang, X., Wang, Z., Ge, W., Shi, T., & Lin, Y. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106972 · Cited by 57
Underwater Optical Imaging: Methods, Applications and Perspectives
Hao, Y., Yuan, Y., Zhang, H., & Zhang, Z. (2024) · Remote Sensing · doi:10.3390/rs16203773 · Cited by 69
Underwater Color Restoration Using U-Net Denoising Autoencoder
Hashisho, Y., Albadawi, M., Krause, T., & von Lukas, U. F. (2019) · International symposium on image and signal processing and analysis/ISPA ... · doi:10.1109/ispa.2019.8868679 · Cited by 55
“Part of these methods [6]–[8] invert the formation of underwater images and construct physical models for image restoration in addition to modifying the image pixel values.”
MethodUnderwater Attentional Generative Adversarial Networks for Image Enhancement
Wang, N., Chen, T., Kong, X., Chen, Y., Wang, R., Gong, Y., & Song, S. (2023) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2023.3261341 · Cited by 55
“In addition, the direction of light propagation is vulnerable to changing by the particles suspended in the water, and thereby, resulting in both blurred edge of object and low contrast [17], [18], [19].”
BackgroundThe Hierarchic Treatment of Marine Ecological Information from Spatial Networks of Benthic Platforms
Aguzzi, J., Chatzievangelou, D., Francescangeli, M., Marini, S., Bonofiglio, F., Fernández, J. D. R., & Danovaro, R. (2020) · Sensors · doi:10.3390/s20061751 · Cited by 54
A Marine Object Detection Algorithm Based on SSD and Feature Enhancement
Hu, K., Lu, F., Lu, M., Deng, Z., & Liu, Y. (2020) · Complexity · doi:10.1155/2020/5476142 · Cited by 65
“…[26], expand the difference between the features of different objects in the image, and suppress uninteresting features. image quality is improved [27], the amount of information is more abundant [28], and the image interpretation and recognition effects are strengthened [29] to meet the needs of…”
BackgroundZhou, J., Wang, Y., Zhang, W., & Li, C. (2021) · Optics Express · doi:10.1364/oe.432900 · Cited by 54
A Dataset for Detection and Segmentation of Underwater Marine Debris in Shallow Waters
Ðuraš, A., Wolf, B. J., Ilioudi, A., Palunko, I., & Schutter, B. D. (2024) · Scientific Data · doi:10.1038/s41597-024-03759-2 · Cited by 65
“Finally, this is followed by a description of the fusion-based image enhancement method 16 which we use as a preprocessing step to improve the visual characteristics of the data and reduce the domain shift.”
MethodWang, H., Frery, A. C., Li, M., & Ren, P. (2023) · Intelligent Marine Technology and Systems · doi:10.1007/s44295-023-00015-y · Cited by 53
“By including the information in the green channel, we can realize a more extensive color recovery while keeping the inherent visual appearance of the image (Ancuti et al. 2018).”
Color correction methods for underwater image enhancement: A systematic literature review
Yong, L., Ang, T. F., Bhatti, U. A., Ku, C. S., Qi, H., & Por, L. Y. (2025) · PLoS ONE · doi:10.1371/journal.pone.0317306 · Cited by 52
“…[39–47] Color transfer-based [48–51] Multi-color spaces-based [46,52–55] Color opponent compensation-based [56,57] Fusion-based [18,20,22,25,29,38,45,50,55,58] Convolutional neural network (CNN)-based [43,46,49,52,53,59–66] Generative adversarial network (GAN)-based [57,67–74]…”
InfluentialLiu, Z., Zhuang, Y., Jia, P., Wu, C., Xu, H., & Liu, Z. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10091204 · Cited by 54
Underwater image enhancement using adaptive standardization and normalization networks
Park, C. W., & Eom, I. K. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107445 · Cited by 53
DGD-cGAN: A dual generator for image dewatering and restoration
González-Sabbagh, S., Robles‐Kelly, A., & Gao, S. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110159 · Cited by 56
Underwater Image Restoration Based on A New Underwater Image Formation Model
Zhang, M., & Peng, J. (2018) · IEEE Access · doi:10.1109/access.2018.2875344 · Cited by 52
“[9] proposed a color balance and fusion method for underwater image enhancement, which is a modified version of their method in [8].”
MethodUnderwater Image Enhancement Based on Local Contrast Correction and Multi-Scale Fusion
Gao, F., Wang, K., Yang, Z., Wang, Y., & Zhang, Q. (2021) · Journal of Marine Science and Engineering · doi:10.3390/jmse9020225 · Cited by 55
“Color restoration: (a) Initial image, (b) He [9], (c) Galdran [32], (d) Galdran [6], (e) Ancuti [11], (f) Ancuti [4], (g) our result.”
BackgroundMethodInfluentialPhISH-Net: Physics Inspired System for High Resolution Underwater Image Enhancement
Chandrasekar, A., Sreenivas, M., & Biswas, S. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00153 · Cited by 61
“This was established in [4] by performing extensive experimentation on a variety of underwater image datasets.”
BackgroundMethodUnderwater visual surveillance: A comprehensive survey
Rout, D. K., Kapoor, M., Subudhi, B. N., Veerakumar, T., Jakhetiya, V., & Bansal, A. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.118367 · Cited by 55
Color Channel Transfer for Image Dehazing
Ancuti, C. O., Ancuți, C., Vleeschouwer, C. D., & Sbert, M. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2932189 · Cited by 50
“In contrast to [26] that depends on manual parameter adjustment, CCT is the first work that demonstrates a general automatic solution for various dehazing applications.”
BackgroundSelf-citationA Review on Image Enhancement and Restoration Techniques for Underwater Optical Imaging Applications
Deluxni, N., Sudhakaran, P., Kitmo, & Ndiaye, M. F. (2023) · IEEE Access · doi:10.1109/access.2023.3322153 · Cited by 51
“From the input image [30], create the double fusion picture: beginning process to adjusting the white color balance, and another process to improve the histogram equalization process.”
MethodA multi-level wavelet-based underwater image enhancement network with color compensation prior
Wang, Y., Hu, S., Yin, S., Deng, Z., & Yang, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122710 · Cited by 54
Underwater image restoration via depth map and illumination estimation based on a single image
Zhou, J., Yang, T., Ren, W., Zhang, D., & Zhang, W. (2021) · Optics Express · doi:10.1364/oe.427839 · Cited by 56
Deep learning based deep-sea automatic image enhancement and animal species classification
López-Vázquez, V., López-Guede, J. M., Chatzievangelou, D., & Aguzzi, J. (2023) · Journal Of Big Data · doi:10.1186/s40537-023-00711-w · Cited by 55
“, as white balance) is the global adjustment of colour intensities to correct the representation of neutral colours [9, 84].”
BackgroundLin, W.-T., Lin, Y.-X., Chen, J.-W., & Hua, K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0911-6_11 · Cited by 48
Image descattering and absorption compensation in underwater polarimetric imaging
Fu, X., Liang, Z., Ding, X., Yu, X., & Wang, Y. (2020) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2020.106115 · Cited by 48
Underwater Color Correction Network With Knowledge Transfer
Lin, P., Wang, Y., Li, Y., Fan, Z., & Fu, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3374598 · Cited by 49
“From left to right are raw underwater images, the results of Retinex-based [8], UDCP [19], UIBLA [20], ColorBalance [10], GDCP [21], Water-Net [28], FUnIE [29], UWCNN [30], CWR [31], Ucolor [32], UCCNet, and UCCNet-KT. corresponding optimal values, the results of the designed pipeline, in general,…”
BackgroundMethodInfluentialSeeing Through the Haze: A Comprehensive Review of Underwater Image Enhancement Techniques
Saoud, L. S., Elmezain, M., Sultan, A., Heshmat, M., Seneviratne, L. D., & Hussain, I. (2024) · IEEE Access · doi:10.1109/access.2024.3465550 · Cited by 47
Underwater salient object detection by combining 2D and 3D visual features
Chen, Z., Gao, H., Zhang, Z., Zhou, H. M., Wang, X., & Tian, Y. T. (2019) · Neurocomputing · doi:10.1016/j.neucom.2018.10.089 · Cited by 53
A Fast Sand-Dust Image Enhancement Algorithm by Blue Channel Compensation and Guided Image Filtering
Cheng, Y., Jia, Z., Lai, H., Yang, J., & Kasabov, N. K. (2020) · IEEE Access · doi:10.1109/access.2020.3034151 · Cited by 51
“The compensation method is proposed in the algorithm implemented in [25].”
InfluentialTurbid Underwater Image Enhancement Based on Parameter-Tuned Stochastic Resonance
Xiao, F., Yuan, F., Huang, Y., & Cheng, E. (2022) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2022.3190517 · Cited by 48
“The classical model-free underwater image enhancement methods are almost learning from the methods applied in the atmosphere, such as histogram-based [9], white balance based method [10], Retinex-based method [11], fusion-based method [12], and so on.”
MethodChang, L., Song, H., Li, M., & Xiang, M. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.01.007 · Cited by 50
MASNet: A Robust Deep Marine Animal Segmentation Network
Fu, Z., Chen, R., Huang, Y., Cheng, E., Ding, X., & Ma, K. (2023) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2023.3252760 · Cited by 57
“For example, the authors proposed a fusion-based UIE method in [6] and an improved version in [22].”
MethodMuñoz, A. M., Moron-Fernández, M.-J., Cascado-Caballero, D., Díaz-del-Río, F., & Real, P. (2023) · Sensors · doi:10.3390/s23104986 · Cited by 50
“…color balance via two-image fusion to promote edge and color contrast is transferred to the recovered image, being reasonably independent of camera settings [53], as well as an alternative approach based on unsharp masking and contrast-limited histogram equalization [54] are some relevant examples.”
MethodNo-reference quality assessment for underwater images
Hou, G., Zhang, S., Lu, T., Li, Y., Pan, Z., & Huang, B. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109293 · Cited by 47
Optical Imaging and Image Restoration Techniques for Deep Ocean Mapping: A Comprehensive Survey
Song, Y., Nakath, D., She, M., & Köser, K. (2022) · PFG – Journal of Photogrammetry Remote Sensing and Geoinformation Science · doi:10.1007/s41064-022-00206-y · Cited by 52
Neural Underwater Scene Representation
Tang, Y., Zhu, C., Wan, R., Xu, C., & Shi, B. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01119 · Cited by 63
“Many physics-based methods use certain priors to simplify the problem, such as dark channel prior [14], white balance [3], or haze line prior [6], and then separate the back-scatter and transmission part.”
MethodWong, S.-L., Paramesran, R., & Taguchi, A. (2018) · Advances in Electrical and Computer Engineering · doi:10.4316/aece.2018.02014 · Cited by 44
Kumar, M., & Bhandari, A. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3004036 · Cited by 36
“In underwater colour image enhancement [32], [33], using Gray world assumption, compensation of red attenuation is done by adding a part of the green channel to the red.”
MethodPixel-Wise Wasserstein Autoencoder for Highly Generative Dehazing
Kim, G., Park, S., & Kwon, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3084743 · Cited by 47
“[29], and FUnIE [45].”
MethodInfluential
Metadata
- Authors
- Ancuti, C. O., Ancuti, C., De Vleeschouwer, C., & Bekaert, P.
- Affiliations
- Politehnica University of Timisoara (RO)
- Hasselt University (BE)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2018-01
- Volume
- 27
- Issue
- 1
- Pages
- 379-393
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2763503841
- Cited by
- 1,357
- References
- 76
- Citations by year
- 2026: 174 · 2025: 260 · 2024: 248 · 2023: 206 · 2022: 181 · 2021: 110 · 2020: 91 · 2019: 61 · 2018: 25
- FWCI
- 20.08
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) (submittedVersion, other-oa)
- Document Server@UHasselt (UHasselt) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Engineering › Media Technology › Image Processing Techniques and Applications
- Keywords
- underwater image enhancement, color balance, image fusion, white balancing, multi-scale fusion, weight map, edge preservation, color contrast, light absorption and scattering, single image enhancement, underwater video
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.