Generalization of the Dark Channel Prior for Single Image Restoration

By Yan-Tsung Peng, Keming Cao, Pamela C. Cosman. IEEE Transactions on Image Processing, 2018

719 citations recorded by the source corpus.

Images degraded by light scattering and absorption, such as hazy, sandstorm, and underwater images, often suffer color distortion and low contrast because of light traveling through turbid media. In order to enhance and restore such images, we first estimate ambient light using the depth-dependent color change. Then, via calculating the difference between the observed intensity and the ambient light, which we call the scene ambient light differential, scene transmission can be estimated. Additionally, adaptive color correction is incorporated into the image formation model (IFM) for removing color casts while restoring contrast. Experimental results on various degraded images demonstrate the new method outperforms other IFM-based methods subjectively and objectively. Our approach can be interpreted as a generalization of the common dark channel prior (DCP) approach to image restoration, and our method reduces to several DCP variants for different special cases of ambient lighting and turbid medium conditions.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ccfa1948f01e6f5811b3b11b6fcc2cd594194139

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. Runmin Cong
4. Dacheng Tao
5. Qingming Huang
6. Saeed Anwar
7. Wenqi Ren
8. Sam Kwong

In Media Technology

1. Chongyi Li
2. Runmin Cong
3. Peixian Zhuang
4. Junhui Hou
5. Chunle Guo
6. Wenqi Ren
7. Saeed Anwar
8. Sam Kwong

Citations in the corpus

• An Underwater Image Enhancement Benchmark Dataset and Beyond (2019, methodology): “From left to right are raw underwater images, and the results of Fusion-based [29], Retinex-based [31], Two-step-based [30], UDCP [35], Red Channel [40], Histogram Prior [42], Regression-based [37], Blurriness-based [43], GDCP [38], and reference images.”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “(c) GDCP [12].”
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators (2023, methodology): “Likewise, the enhancement results of GDCP [30] also exhibit obvious color distortion, but also achieve high scores on the non-reference metrics.”
• Underwater Image Enhancement via Weighted Wavelet Visual Perception Fusion (2024, methodology): “In terms of contrast enhancement, GDCP [26], DTVR [6], GIFM [31], FUnIE-GAN [53], and SGUIE-Net [2] are weaker than UIECˆ2-Net [50] and PUIE-Net [55].”
• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, positive): “ICENet [26] and ICENetv2 [27] show that the two-branch network structure like BiSeNet [11] with a finer spatial branch and a deep context semantic branch is very suitable to segment the river ice with scale diversity characteristic.”
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, methodology): “In [30], the homogeneous background light is estimated based on the depth-dependent color change.”