LIDN: A novel light invariant image dehazing network

Ali, Asfak; Ghosh, Avra; Chaudhuri, Sheli Sinha

doi:10.1016/j.engappai.2023.106830

Cited by 15 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-Learning based Contrast Maximizing [62] Dark Channel Prior [36] Dehaze net [63] AdaFM-Net [12] MPAB [91] QCNN-H [72] Deep-CNN [87] LIDN [85] RRANet [13] NLNet [92] DLA [94] SCR-Net [93] AFF-Net [84] LMFAN [89] LSA-Module [88] CBAM [90] Proximal DehazeNet [105] NIN Dehazenet [111] MSCNN [64] AOD net [67] Improved Dark Channel [61] DCP Using Histogram Specification [19] DCP Using Guided Filter [22,25,26,29] ICA [39] Dark Channel Anisotropic diffusion [38] Color Attenuation Prior [60] Attention Mechanism based…”

Section: Single Image Dehazingmentioning

confidence: 99%

“…The attention mechanism is learned through trainable weights, which are updated during training. The light invariant dehazing network (LIDN) 85 has been introduced for end-to-end real-time image dehazing. In order to train the LIDN, the quadruplet loss coefficient 86 is implemented, which results in a sharper dehazed image and fewer artifacts.…”

Section: Attention Mechanisms Incorporating Attention Mechanisms Into...mentioning

confidence: 99%

“…The quantitative and qualitative measures to compare the effectiveness of the dehaze methods are evaluated. Among the different haze removal, the most frequently used methods include Fattal, 39 Tarel, 40 He, 36 MSCNN, 64 AOD Net, 67 dehazeNet, 63 Dehaze-GAN, 100 SCR-Net, 93 QCNN-H, 72 Deep CNN, 87 LIDN, 85 and RRANet, 13 which have been reviewed and experimental evaluation carried out on the different available dehazing datasets.…”

Section: Attention Mechanisms Incorporating Attention Mechanisms Into...mentioning

confidence: 99%

“…The ground truth image is provided or not provided for the quality measurements such as peak signal-to-noise ratio (PSNR), 129,130 mean squared error (MSE), 130 structural similarity index metric (SSIM), 61,129 natural image quality evaluator (NIQE), 131 visibility index (VI), [132][133][134][135][136][137] and realness index (RI). 72,85,87 Ground truth image is a haze-free image of the same original hazy image. However, haze-free is produced when some haze removal techniques are applied to the hazy image datasets.…”

Section: Quantitative Measurementsmentioning

confidence: 99%

“…G 2 a ðRÞ and G 2 b ðRÞ are partial derivatives of the image at R. G 1 ðRÞ and G 2 ðRÞ are the gradient modules of the dehaze and haze images, α is the adjustable parameters between the gradient module and transmission map. Several dehazing techniques 13,72,85,87,[132][133][134][135][136][137][139][140][141][142][143][144][145][146][147] introduce artifacts or distort the image, which reduces visibility. As an outcome, while the initial hazy images are original images without these degradations, some methods also have to consider the accuracy of the dehazing outcomes when evaluating a dehazing technique.…”

Section: Quantitative Measurementsmentioning

confidence: 99%

See 4 more Smart Citations

Review and evaluation of recent advancements in image dehazing techniques for vision improvement and visualization

Shit,

Ray

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Vision gets obscured in adverse weather conditions, such as heavy downpours, dense fog, haze, snowfall, etc., which increase the number of road accidents yearly. Modern methodologies are being developed at various academics and laboratories to enhance visibility in such adverse weather with the help of technologies. We review different dehazing techniques in many applications, such as outdoor surveillance, underwater navigation, intelligent transportation systems, object detection, etc. Dehazing is achieved in four primary steps: the capture of hazy images, estimation of atmospheric light with transmission map, image enhancement, and restoration. These four dehazing procedures allow for a step-by-step method for resolving the complicated haze removal issue. Furthermore, it also explores the limitations of existing deep learning-based methods with the available datasets and the challenges of the algorithms for enhancing visibility in adverse weather. Reviewed techniques reveal gaps in the case of remote sensing, satellite, and telescopic imaging. In the experimental analysis of various image dehazing approaches, one can learn the effectiveness of each phase in the image dehazing process and create more effective dehazing techniques.

show abstract