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 501–600 of 1,000
Men, C., Li, J., Liu, Z., Zhang, X., & Hou, G. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.113565 · Cited by 11
Song, W., Nabahirwa, E., Zhang, M., Fang, Y., & Ni, Z. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-00895-z · Cited by 12
WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement
Cheng, C.-H., Lee, J.-W., Lee, C.-M., & Hsu, C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00212 · Cited by 11
“(2) Non-reference datasets : We evaluate the UIEB-pretrained model on Challenging-60 [20] and U45 [23], and further assess color correction performance on the Color-Check7 [3] dataset.”
InfluentialUnderwater Image Restoration via Non-Convex Non-Smooth Variation and Thermal Exchange Optimization
Jiao, Q., Liu, M., Li, P., Dong, L., Hui, M., Kong, L., & Zhao, Y. (2021) · Journal of Marine Science and Engineering · doi:10.3390/jmse9060570 · Cited by 11
“The IFM-free methods, such as Retinex [7], Gray-World algorithm [8], and multi-scale fusion [9,10], are also called image enhancement methods, which improve the contrast without using underwater imaging models.”
MethodDesign of Fractional Calculus based differentiator for edge detection in color images
Mishra, S. K., Singh, K. K., Dixit, R., & Bajpai, M. K. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11187-2 · Cited by 11
MDNet: A Fusion Generative Adversarial Network for Underwater Image Enhancement
Zhang, S., Zhao, S., An, D. U., Li, D., & Zhao, R. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11061183 · Cited by 12
“The combination of multiple methods can provide multi-scale features, overcome the limitations of a single method to a certain extent, and achieve better results [13].”
BackgroundUnderwater Image Enhancement with an Adaptive Self Supervised Network
Khan, R., Mehmood, A., Akbar, S., & Zheng, Z. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00235 · Cited by 11
“images, and color checker images from [24].”
Transmission and Color-guided Network for Underwater Image Enhancement
Mu, P., Fang, J., Qian, H., & Bai, C. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00232 · Cited by 16
Underwater Image Enhancement and Super-Resolution Using Implicit Neural Networks
Chu, X., Fu, Z., Yu, S., Tu, X., Huang, Y., & Ding, X. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222035 · Cited by 14
“( * Corresponding author: Xinghao Ding, dxh@xmu.edu.cn) ample, the visual quality of underwater images has been enhanced based on hand-crafted priors [1, 2].”
BackgroundUnderwater Image Enhancement Network Based on Dual Layers Regression
Jia, H., Xiao, Y., Wang, Q., Chen, X., Han, Z. J., & Tang, Y. (2024) · Electronics · doi:10.3390/electronics13010196 · Cited by 13
“Ancuti et al. [27] subsequently improved this strategy.”
BackgroundHassan, M. F., Lang, W. S., & Paramesran, R. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19245-1 · Cited by 12
“…i , j ) represent the red, green, and blue color channels of an image with the interval [0,1], ¯ G and ¯ B are the global mean values of G ( i , j ) and B ( i , j ) . α b is a constant parameter equal to 1, which is deemed suitable for various illumination conditions and acquisition settings [27].”
Development of an Underwater Detection Robot for the Structures with Pile Foundation
Zhang, W., Zhu, K., Yang, Z., Ye, Y., Ding, J., & Gan, J. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12071051 · Cited by 11
MDA-Net: A Multidistribution Aware Network for Underwater Image Enhancement
Liu, X., Jiang, Y., Wang, Y., Liu, T., & Wang, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3524758 · Cited by 23
Sankpal, S. S., & Deshpande, S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1513-8_95 · Cited by 11
Modified clipping based image enhancement scheme using difference of histogram bins
Kandhway, P., & Bhandari, A. K. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0111 · Cited by 11
gong, K., & Hua, D. (2022) · 2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA) · doi:10.1109/cvidliccea56201.2022.9824370 · Cited by 11
Non-Local Retinex Based Dehazing and Low Light Enhancement of Images
Hari, U., & Bevi, A. R. (2022) · Traitement du signal · doi:10.18280/ts.390313 · Cited by 11
“Ancuti et al. [31] resolved a novel submerged image enrichment utilizing different fusion methods and further developed the low light pictures caught underwater.”
MethodUnderwater Accompanying Robot Based on SSDLite Gesture Recognition
Liu, T., Zhu, Y., Wu, K., & Yuan, F. (2022) · Applied Sciences · doi:10.3390/app12189131 · Cited by 12
“Image Enhancement Performance We compared and analyzed the proposed Estimation Network image enhancement algorithm with other methods, including simple white balance, underwater dark channel, multi-scale fusion [42], DN-based [43], and UGAN [44].”
MethodMulTNet: A Multi-Scale Transformer Network for Marine Image Segmentation toward Fishing
Xu, X., Qin, Y., Xi, D., Ming, R., & Xia, J. (2022) · Sensors · doi:10.3390/s22197224 · Cited by 11
Li, T., & Zhou, T. (2022) · PLoS ONE · doi:10.1371/journal.pone.0275107 · Cited by 11
Prasath, R., & Kumanan, T. (2018) · The Imaging Science Journal · doi:10.1080/13682199.2018.1552356 · Cited by 13
“In 2018, Codruta et al. [4] invented a new method to e ff ectively improve the captured underwater images as well as degenerated images by means of absorption and scattering.”
BackgroundMethodInfluentialOptically guided level set for underwater object segmentation
Chen, Z., Qiu, N., Song, H., Xu, L., & Xiong, Y. (2019) · Optics Express · doi:10.1364/oe.27.008819 · Cited by 11
Single Image Restoration for Participating Media Based on Prior Fusion
Gaya, J. F. D. O., Duarte, A., Codevilla, F., Drews, P., & Botelho, S. S. D. C. (2019) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2018.2881388 · Cited by 11
“Recently, Ancuti et al.(23) introduced also a preprocessing step allowing us to apply the DCP on underwater images leading to impressive results.”
BackgroundImprovement of underwater colour correction using standard deviation ratio
Moon, S. W., Lee, H. S., & Eom, I. K. (2020) · Electronics Letters · doi:10.1049/el.2020.1796 · Cited by 11
Underwater image enhancement based on weighted guided filter image fusion
Xiang, D., Wang, H., Zhou, Z., Zhao, H., Gao, P., Zhang, J., & Shan, C. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01432-7 · Cited by 10
“For comparing color methods, we chose white balance [37], ACC [36], and our color correction method (ACPR).”
Robust underwater object tracking with image enhancement and two-step feature compression
Li, J., Xue, C., Luo, X., Fu, Y., & Lin, B. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01755-y · Cited by 10
“For a more comprehensive discussion of underwater image enhancement techniques, refer to Reference [55].”
CD-UDepth: Complementary dual-source information fusion for underwater monocular depth estimation
Guo, J., Ma, J., Sun, F., Gao, Z., García‐Fernández, Á. F., Liang, H., Zhu, X., & Ding, W. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102961 · Cited by 14
CA-Net: Cascaded Adaptive Network for Underwater Image Enhancement
Zhou, X., Peng, M., Jiang, Q., Cong, R., Wang, J., & Chen, Y. (2025) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2024.3501399 · Cited by 14
“Early UIE methods can be categorized into physical model-free meth-ods [5], [6], [7], [8], [9] and physical model-based methods [10], [11], [12], [13], [14], [15], [16], [17].”
UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors
Srinath, S., Chandrasekar, A., Jamadagni, H., Soundararajan, R., & Prathosh, A. P. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00872 · Cited by 15
“Popular methods employ various image processing techniques [4, 5, 24, 32, 53, 54,84,90], utilize priors [8,12–14,19,60,70,75,88], or rely on an underwater image formation model [1, 7, 29, 58, 79, 85,89].”
An Analytical Review of Underwater Image Enhancement Techniques
Gogoi, K., Baruah, S. K., Konwar, U., Mahanta, R., Boruah, A., Sarma, D., & Kakoty, N. M. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.531 · Cited by 10
CDDU: Convolutional Dictionary Deep Unfolding Network for Underwater Image Enhancement
Chang, B., Yuan, G., & Li, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3584116 · Cited by 14
“Specifically, adjustments were made at the pixel level, typically in spatial domains, using techniques such as pixel stretching algorithms [5], pixel distribution algorithms [30], and image fusion algorithms [31], [32].”
A multi-scale feature extraction and attention aggregation network for underwater image enhancement
Yan, X., Liu, X., Qu, R., Ning, B., Xu, F., Wang, Y., & Li, F. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129226 · Cited by 15
Rehman, M. U., Bakht, A. B., & Hussain, I. (2026) · Ecological Informatics · doi:10.1016/j.ecoinf.2026.103771 · Cited by 10
Underwater Image Dehazing Using The Color Space Dimensionality Reduction Prior
Liu, Y., Rong, S., Cao, X., Li, T., & He, B. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190901 · Cited by 10
“Ancuti and Ancuti et al. [20-22] developed a series of dehazing methods based on fusion theory.”
MethodAn Enhancement of Underwater Images using DCP and CLAHE Algorithm
Malathi, V., & Manikandan, A. (2019) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.a9607.129219 · Cited by 10
“Image dehazing is a process to remove haze or fog effects from the poor quality images [4].”
BackgroundUnderwater vision enhancement based on GAN with dehazing evaluation
Yu, H., Li, X., Feng, Y., & Han, S. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03789-6 · Cited by 14
“The degradation of underwater vision caused by the absorption and scattering of light in water [1].”
BackgroundComparison of Various Proposed Techniques for Processing of Different Images
Garg, R., & Sandhu, A. K. (2022) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite53722.2022.9823780 · Cited by 10
Blind Text Image Deblurring Algorithm Based on Multi-Scale Fusion and Sparse Priors
Li, Z., Yang, M., Cheng, L., & Jia, X. (2023) · IEEE Access · doi:10.1109/access.2023.3245150 · Cited by 10
“Inspired by the work of Ancuti et al. [11], we use multi-scale fusion to deal with the influence of the brightness information of the recovered blur kernel.”
MethodScene recovery: Combining visual enhancement and resolution improvement
Zhang, H., Qi, T., & Zeng, T. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110529 · Cited by 10
Fusion-Based Underwater Image Enhancement by Weight Map Techniques
Honnutagi, P., Mytri, V. D., & Lalitha, Y. S. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-1280-9_31 · Cited by 10
Enhanced image no‐reference quality assessment based on colour space distribution
Liu, H., Li, C., Zhang, D., Zhou, Y., & Du, S. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0856 · Cited by 10
“Next, we construct reference images and use Liu et al. [37], Ancuti et al. [38] and Pan et al. [39] to enhance underwater images.”
BackgroundMethodInfluentialBackground Scene Recovery From an Image Looking Through Colored Glass
Wang, C., Xu, D., Wan, R., He, B., Shi, B., & Duan, L. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3152390 · Cited by 10
“ums like water [4], [5] or thick atmosphere [31], [41], which also lead to color deviations from the clear image taken without the medium blocking in front of the camera.”
BackgroundFCNN: fusion-based underwater image enhancement using multilayer convolution neural network
Verma, G., Kumar, M. P. P., & Raikwar, S. C. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.6.063039 · Cited by 10
“27 utilized fusion approach for color balancing.”
Turbidity-adaptive underwater image enhancement method using image fusion
Han, B., Wang, H., Luo, X., Liang, C., Yang, X., Liu, S., & Lin, Y. (2022) · Frontiers of Mechanical Engineering · doi:10.1007/s11465-021-0669-8 · Cited by 10
DRC: Chromatic aberration intensity priors for underwater image enhancement
Liu, Q., He, Z., Zhang, D., Zhang, W., Lin, Z., & Sohel, F. A. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104065 · Cited by 10
Underwater visibility restoration using dehazing, contrast enhancement and filtering
Chaudhry, A. M., Riaz, M. M., & Ghafoor, A. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07922-5 · Cited by 10
Recovery for underwater image degradation with multi-stage progressive enhancement
Liu, J., Liu, Z., Wei, Y., & Ouyang, W. (2022) · Optics Express · doi:10.1364/oe.453387 · Cited by 10
Kaur, M., & Vijay, S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12535-6 · Cited by 10
“The simulation results of different enhancement techniques presented by the Ancuti in 2018 [1] and Yong-Jie Li in 2019 [3] are given in the Table 1: From the Fig.”
MethodA diverse underwater image formation model for underwater image restoration
Ullah, S., Hassan, N., & Bhatti, N. (2024) · Earth Science Informatics · doi:10.1007/s12145-024-01462-9 · Cited by 12
Wang, Y., Ma, Y., Li, Y., Zhang, J., Mi, Z., & Fu, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3504000 · Cited by 10
“Methods : We compare the proposed method with the following nine state-of-the-art underwater image enhancement methods: RDCP [11], ROP [13], IBLA [12], BR [6], FR [7], Fusion [8], Ucolor [5], UIESS [9], and UWCNN [10].”
InfluentialAttention-based lightweight deep hybrid CNN framework for image restoration
Karthikeyan, V., & Visu, Y. P. (2024) · The Imaging Science Journal · doi:10.1080/13682199.2024.2439731 · Cited by 11
Underwater Image Enhancement via Piecewise Colour Balancing and Multiscale Enhancement Fusion
Liang, Z., Huang, H., Zhang, W., Song, H., Wan, X., Wang, C., Huang, L., & Zhuang, P. (2025) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2025.3555684 · Cited by 9
“Thus, Ancuti et al. [25] revised the exposure weight map to improve upon their previous work, and the enhanced image demonstrated that their method is useful for compressing undesirable artifacts.”
Ji, X., Wang, X., Hao, L., Cai, C., Dai, C., & Liu, R. W. (2025) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2025.3611669 · Cited by 9
“Ancuti et al. [33] further improved the white balance theory and presented a multiscale fusion strategy that aggregates the color-compensated and white-balanced alternatives of the degraded underwater images.”
Toward Better Than Pseudo-Reference in Underwater Image Enhancement
Liu, Y., Jiang, Q., Li, X., Luo, T., & Ren, W. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3611138 · Cited by 9
Construction of Smooth Biorthogonal Waves on Triangulated Spaces
Bityukov, Y. I., Deniskin, Y., & Pocebneva, I. V. (2019) · International Russian Automation Conference (RusAutoCon) · doi:10.1109/rusautocon.2019.8867785 · Cited by 9
Contrast enhancement of underwater images using conditional generative adversarial network
Agarwal, A., Gupta, S., & Vashishath, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17158-z · Cited by 9
“• Under water color image quality evaluation (UCIQE) UCIQE [17] is a linear combination of saturation, Chroma and contrast.”
Mishra, A. K., Kumar, M., & Choudhry, M. S. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03047-x · Cited by 9
“The result shows that the proposed approach gives better visual images compared to HLRP [35], MPORU [36], MIL [39], CBF [17], TEBCF [41], and MWMGF [42].”
RGB/Event signal fusion framework for multi-degraded underwater image enhancement
Bi, X., Wang, P., Guo, W., Zha, F., & Sun, L. (2024) · Frontiers in Marine Science · doi:10.3389/fmars.2024.1366815 · Cited by 11
Underwater Image Enhancement by Illumination Map Estimation and Adaptive High-Frequency Gain
Cui, Z., Yang, C., Wang, S., Wang, X., Duan, H., & Na, J. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3409435 · Cited by 9
“Ancuti et al. [18] introduced a multiscale fusion strategy for improving texture and edge detail information in underwater image.”
BackgroundMethodZhang, Y., Chandler, D. M., & Leszczuk, M. (2024) · Optics Express · doi:10.1364/oe.523951 · Cited by 9
GUCL: Generalization of underwater color-line model for underwater image enhancement
Yao, X., Liang, X., Yu, H., Liu, Z., & Zhao, Z. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109471 · Cited by 9
Underwater Image Enhancement Fusion Method Guided by Salient Region Detection
Yang, J., Huang, H., Lin, F., Gao, X., Jin, J., & Zhang, B. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12081383 · Cited by 9
“Although IBLA [12] and CBAF [45] perform well in underwater scenes, the picture still suffers from fog and blur.”
BackgroundMethodInfluentialDNIM: Deep-sea netting intelligent enhancement and exposure monitoring using bio-vision
An, S., Xu, L., Deng, Z., & Zhang, H.-P. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102629 · Cited by 9
Ji, X., Wang, X., Leng, N., Hao, L., & Guo, H. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105256 · Cited by 10
Toward Individual Tone Preference in Underwater Image Enhancement
Liu, X., Zhao, Y., Chi, K., Zhang, Z., Chen, Y., & Jia, W. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3485030 · Cited by 9
“(g) Fusion [12].”
MethodInfluentialYao, X., Liang, X., Yu, H., & Liu, Z. (2024) · Earth Science Informatics · doi:10.1007/s12145-024-01620-z · Cited by 9
“We select some images taken by different cameras from Color-Check7 dataset (Ancuti et al. 2017), and the comparison results are shown in Fig.”
Transmission map and background light guided enhancement of unpaired underwater image
Cheng, S., Jin, Z., Wu, X., & Liang, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129270 · Cited by 10
Dual-stream feature pyramid network with task interaction for underwater object detection
Zhang, W., Wang, H., Li, H., Li, Y., Song, T., Liu, H., & Wang, G. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105199 · Cited by 10
Intensity difference prior with spatial-channel weighted fusion for underwater image restoration
Shang, J., Li, Y., Hu, X., & Yuan, J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103203 · Cited by 9
Underwater Image Enhancement via Color Balance and Stationary Wavelet Based Fusion
Yadav, S., & Raj, K. (2020) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon50539.2020.9298231 · Cited by 9
“2) Sharpening: Sharpening is a most commonly used technique to highlight the edges and details of images that cannot possible to the gamma correction [1].”
BackgroundMethodResultInfluentialImage Pre-processing and Segmentation for Real-Time Subsea Corrosion Inspection
Pirie, C., & Moreno‐García, C. F. (2021) · Proceedings of the international neural networks society · doi:10.1007/978-3-030-80568-5_19 · Cited by 11
Jointly adversarial networks for wavelength compensation and dehazing of underwater images
Fu, X., Ding, X., Liang, Z., & Wang, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14871-7 · Cited by 9
“[2] modified their previous work to improve the color of resultant images and reduce the effects of over-exposure.”
BackgroundTao, Y., Dong, L., Xu, L., Chen, G., & Xu, W. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15153-y · Cited by 9
“[2] proposed a new fusion strategy later, which was developed on the blending of the sharpened version and the gamma-corrected version directly derived from a color-corrected and white-balancing version of original underwater image.”
BackgroundMethodInfluentialUnderwater image quality assessment
Yang, X., Li, J., Liang, W., Wang, D., Zhao, J., & Xia, X. (2023) · Journal of the Optical Society of America A · doi:10.1364/josaa.485307 · Cited by 9
Lin, S., Zhang, R., Ning, Z., & Luo, J. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11061221 · Cited by 9
Reverse gamma correction based GARCH model for underwater image dehazing and detail exposure
Alenezi, F. S., Armghan, A., Alharbi, A. G., Öztürk, Ş., Althubiti, S. A., & Mansour, R. F. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120856 · Cited by 9
Underwater image enhancement based on adaptive color correction and multi-scale fusion
Shi, J., Yu, S., Li, H., Zhang, X., & Liu, C. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15652-y · Cited by 9
A no-reference underwater image quality evaluator via quality-aware features
Zhang, S., Li, Y., Tan, L., Yang, H., & Hou, G. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.103979 · Cited by 9
Label-Aware Calibration and Relation-Preserving in Visual Intention Understanding
Shi, Q., Ye, M., Huang, W., Ruan, W., & Du, B. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3380250 · Cited by 12
“T HE purpose of computer vision is to enable computers to obtain meaningful information from visual inputs such as images and videos [1], [2], [3], [4], [5], [6].”
BackgroundUnderwater Image Enhancement via L2 based Laplacian Pyramid Fusion
Wang, Y., Yang, Y. X., Ding, X., & Fu, X. (2019) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.23919/oceans40490.2019.8962535 · Cited by 9
“around image fusion, such as [11][12][13][14].”
Single Image-based Enhancement Techniques for Underwater Optical Imaging
Kim, D. G., & Kim, S. M. (2020) · Journal of Ocean Engineering and Technology · doi:10.26748/ksoe.2020.030 · Cited by 9
“The image fusion method was also proposed to combine the characteristics enhanced in multiple image processing steps (Ancuti et al., 2017).”
BackgroundMethodEnhancing visibility in hazy conditions: A multimodal multispectral image dehazing approach
Mahdizadeh, M., Ye, P., & Zhao, S. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104407 · Cited by 8
Dual-channel prior-based deep unfolding with contrastive learning for underwater image enhancement
Pham, T. T., Truong, M. T. N., Yu, H. H., & Lee, C. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104500 · Cited by 8
Liu, W., He, S., Xu, J., Chen, Y., Li, W., Shu, H., Duan, P., & Zhu, F. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.113625 · Cited by 8
Underwater image enhancement using hybrid transformers and evolutionary particle swarm optimization
Kumar, A., Berar, G., Sharma, M., Sakshi, Noonia, A., & Verma, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-14439-5 · Cited by 8
“Ancuti et al. 14 proposed an underwater image enhancement approach using fusion.”
Yang, Z., Hao, C., Lu, Y., Su, Y., Zhang, Y., Zhang, J., & Tian, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3607694 · Cited by 8
Impact of Underwater Image Enhancement on Feature Matching
Summers, J. M., Jones, M. W., & Seale, C. (2025) · Sensors · doi:10.3390/s25226966 · Cited by 8
“We can see in both datasets that videos enhanced by classical methods performed poorly, with Demir and Kaplan [72] coming last in every detector except SuperPoint, and Ancuti et al. [19] coming in the bottom three apart from a few notable exceptions.”
InfluentialPyUIE: A Coarse-to-Fine Deep Pyramid Network for Underwater Image Enhancement
Jiang, W., Tan, Y., Qiu, Z., Wang, Z., Yu, Y., & Jiang, Q. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3651111 · Cited by 9
“Ucolor [62] attempts to guide transmission estimation via GDCP [43], but its adaptability to different underwater environments and image degradation types may be limited.”
PHISWID: physics-inspired underwater image data set synthesized from RGB-D images
Kaneko, R., Ueda, T., Higashi, H., & Tanaka, Y. (2026) · APSIPA Transactions on Signal and Information Processing · doi:10.1108/atsip-02-2026-001 · Cited by 9
“Various underwater image datasets and enhancement meth-ods have tackled to address this lack of ground-truth images [11], [13], [14], [34]–[38].”
SubmergeStyleGAN: Synthetic Underwater Data Generation with Style Transfer for Domain Adaptation
Fathy, M. E., Mohamed, S. A., Awad, M. I., & Munim, H. E. A. E. (2023) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta60407.2023.00081 · Cited by 11
“This module was compared against various state-of-the-art techniques, including BAL [35], fusion-based enhancement by Ancuti et al. [31], and UWCNN [36].”
MethodRestoration on High Turbidity Water Images Under Near-Field Illumination Using a Light-Field Camera
Zhou, S., Zhang, Z., Liu, Y., & Tian, J. (2024) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2024.3420881 · Cited by 8
“Based on this work, Cosmin Ancuti et al. [24] improve global contrast of underwater images by blending white-balanced and color-compensatedimages.”
BackgroundZhang, B., Fang, J., Li, Y., Wang, Y., Zhou, Q., & Wang, X. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12071175 · Cited by 8
Kurinjimalar, R., Pradeep, J., & Harikrishnan, M. (2024) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic61668.2024.10730935 · Cited by 8
Multi-Level Perception Assessment for Underwater Image Enhancement
Xu, Y., Lin, Y., He, N., Wang, X., & Zhao, T. (2025) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2025.3525972 · Cited by 8
“…underwater images and 900 enhanced images produced by 15 UIE algorithms, including 12 traditional UIE algorithms (i.e., Bayesian-Retinex [47], CBF [48], CHS [49], HP [50], L 2 UWE [51], Retinex-based [2], two-step-based [11], UWB-VCSE [52], UIBLA [44], RCP [53], UNTV [54], UTV [55]), and 3 deep…”
RSUIA: Dynamic No-Reference Underwater Image Assessment via Reinforcement Sequences
Zhou, J., Liu, C., Zhang, D., He, Z., Sohel, F. A., & Jiang, Q. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535308 · Cited by 8
“Model-free methods employ classical image processing techniques, such as color balance [23], and image fusion [23], [24].”
Multiscale Fusion Method for the Enhancement of Low-Light Underwater Images
Zhou, J., Zhang, D., & Zhang, W. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/7095248 · Cited by 8
“We employ two metrics due to avoiding the deviation from qualitative comparison: UIQM [32] and PCQI [32].”
BackgroundMethodInfluentialRobust underwater image enhancement method based on natural light and reflectivity
Deng, X., Zhang, Y., Wang, H., & Hu, H. (2020) · Journal of the Optical Society of America A · doi:10.1364/josaa.400199 · Cited by 8
Underwater image enhancement algorithm combining color correction and multi-scale fusion
Fan, X., Lü, L., Shi, P., & Zhang, X. (2021) · International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · doi:10.1109/ecti-con51831.2021.9454733 · Cited by 8
“The fusion method of Ancuti’s algorithm [7] improves the image quality very obviously, and the only shortcoming is that the deblurring of deep water images is not ideal.”
MethodResultMaritime filtering for images and videos
Chan, Y.-T. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116477 · Cited by 8
Underwater image enhancement method based on entropy weight fusion
Du, X. D., Sun, X., Wang, K., Yang, J., & Wang, C. (2022) · Computer Animation and Virtual Worlds · doi:10.1002/cav.2098 · Cited by 8
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.