Color Balance and Fusion for Underwater Image Enhancement

By Codruta Orniana Ancuti, Cosmin Ancuți, C. De Vleeschouwer, Philippe Bekaert. IEEE Transactions on Image Processing, 2018

1,171 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/2edc7ee4ef1b19d104f34395f4e977afac12ea64

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. Wenqi Ren
4. Radu Timofte
5. Runmin Cong
6. Saeed Anwar
7. Cosmin Ancuți
8. Codruta Orniana Ancuti

In Media Technology

1. Chongyi Li
2. Runmin Cong
3. Wenqi Ren
4. Saeed Anwar
5. Chunle Guo
6. Radu Timofte
7. Shai Avidan
8. Dana Berman

Citations in the corpus

• Underwater Image Enhancement via Weighted Wavelet Visual Perception Fusion (2024, methodology): “Traditional fusion methods [9], [16], [40] rely on multiple feature maps to integrate different enhanced versions to obtain a high-quality underwater image, but too many features make the robustness of the algorithm challenging and the effectiveness of these feature maps varies widely.”
• Internet of Underwater Things and Big Marine Data Analytics—A Comprehensive Survey (2020, methodology): “Additional improvements may also be attained by software methods, such as wavelength compensation and color reconstruction [135], [197] both in active and passive underwater photography.”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, neutral): “We first extract the color block part in these results, and then match the size and orientation of color block part to the ground-truth ColorChecker of the 24 X-Rite Chart [11], (e) CBF [17], (f) GDCP [12], (g) UWCNN [27], (h) Waternet [28], (i) L1 [6], and (j) Ours. image.”
• Sea-Thru: A Method for Removing Water From Underwater Images (2019, background): “After a meticulous survey of these methods, authors in [7] found that DCP-based ones [21, 50] were not able to consistently correct colors, and others [3, 4, 5, 25] were designed to enhance images rather than achieve physically accurate corrections.”
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators (2023, background): “This adjustment is generally performed in the spatial domain, such as dynamic pixel range stretching [12], pixel distribution adjustment [13], and image fusion [14],”
• Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, methodology): “[21], [23], [24] and Emberton et al .”
• U-Shape Transformer for Underwater Image Enhancement (2021, methodology): “[65] to employ CIEDE2000 [66] to measure the relative differences between the corresponding color patches of ground-truth Macbeth Color Checker and the enhancement results of these comparison methods.”
• Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light (2019, background): “fusion strategy to avoid the artifacts of the reconstructed image [34].”
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, methodology): “At last, we followed the previous method [25] to employ CIEDE2000 [57] to measure the relative perceptual differences between the corresponding color patches of ground-truth Macbeth Color Checker and those of enhanced results.”
• Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images (2019, background): “The problem is related also to underwater image dehazing [11], [12], [13], [14].”