Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior

By Chongyi Li, Jichang Guo, Runmin Cong, Yanwei Pang, Bo Wang. IEEE Transactions on Image Processing, 2016

813 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/170b2ab193376bb447477d9021e4d858ae946357

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chongyi Li
2. Chunle Guo
3. Chunli Zhu
4. Liheng Bian
5. Lintao Peng
6. Runmin Cong
7. Wenqi Ren
8. Peixian Zhuang

Citations in the corpus

• Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light (2019, background): “…Drews-Jr [9] Underwater DCP on g,b R/ CC RMSE UHP [7] Color distribution R RGB Median angle NOM [8] Underwater DCP R Li [23] Underwater DCP R LDP [24] Histogram distribution prior R, S, CC MSE, PSNR, Entropy, PCQI, UCIQE Peng [12] Blurriness& Light Absorption R, S PSNR, SSIM, BRISQUE, UIQM WCID…”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, neutral): “We further test the ColorChecker 24 X-Rite Chart image [39] to exhibit color correction accuracy of our method.”
• An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, methodology): “[42] proposed an underwater image enhancement method based on the minimum information loss principle and histogram distribution prior.”
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, background): “[4], Peng et al .”
• A deep CNN method for underwater image enhancement (2017, methodology): “Following the previous work in [7] [9], we used the benchmark video to evaluate the effectiveness and robustness of UIE-Net.”
• UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space (2021, methodology): “Early underwater image enhancement methods often directly use traditional techniques( e.g. histogram equalization based methods,and physical-based methods [2], [3]).”
• Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network (2020, background): “Image enhancement methods [3]–[6] without underwater physical parameters focus on adjusting image pixel values to produce appealing results.”
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators (2023, methodology): “These methods usually rely on some priors, such as red channel prior [22], underwater dark channel prior [18], [20], minimum information prior [21], general dark channel prior [17], [30], and blurriness prior [19].”
• U-Shape Transformer for Underwater Image Enhancement (2021, methodology): “Among them, visual prior-based UIE methods [2, 11, 13, 17, 18, 29] mainly concentrated on improving the visual quality of underwater images by modifying pixel values from the perspectives of contrast, brightness and saturation.”