Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing

Das, Sourya Dipta; Dutta, Saikat

doi:10.1109/cvprw50498.2020.00249

Cited by 57 publications

(37 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acronymum Code Availability Fattal [5] FAT YES Kratz et al [15] KRATZ YES He et al [4] DCP/DCP_F YES Tarrel et al [8] TFV YES Meng et al [11] BCCR YES Sulami et al [12] ATML YES Choi [21] DEF YES Zu et al [13] CAP YES Bermann et al [14] NLD YES Chen et al [10] GRM YES Galdran [17] AMEF YES Fattal [6] -NO Tan [7] -NO Ancuti et al [20] -NO Wu et al [47] -NO Zheng et al [18] -NO Zhu et al [19] -NO Ren et al [22] M_NN YES Cai et al [23] DE_Z YES Li et al [26] AOD YES Engin et al [29] CY_D YES Qin et al [36] FFA_Net YES Sourya et al [39] DMPH YES Shao et al [48] -NO Ren et al [31] -NO Dong et al [37] -NO Zhang et al [24] -NO Dong et al [38] -NO Yang et al [30] -NO Swami et al [28] -NO Dudhane et al [32] -NO Ren et al [33] -NO Li et al [34] -NO Li et al [35] -NO Pang et al [25] -NO Shen et al [40] -NO…”

Section: Methodsmentioning

confidence: 99%

“…Content may change prior to final publication. (a) M_NN [22] (b) AOD [26] (c) DE_Z [23] (d) CY_D [29] (e) FFA_Net [36] (f) DMPH [39] This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ This article has been accepted for publication in a future issue of this journal, but has not been fully edited.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Objective Evaluation of Single Image De-Hazing Techniques

Artusi

Raftopoulos

2021

IEEE Access

View full text Add to dashboard Cite

Real-world environment, where images are acquired with digital camera, may be subject to sever climatic conditions such as haze that may drastically reduce the quality performance of sophisticated computer vision algorithms used for various tasks, e.g., tracking, detection, classification etc. Even though several single image de-hazing techniques have been recently proposed with many deep-learning approaches among them, a general statistical framework that would permit an objective performance evaluation has not been independently introduced yet. In this manuscript, certain performance metrics that emphasize different aspects of image quality, output ranges and polarity, are identified and combined into a single performance indicator derived in an unbiased manner. A general methodology is thus introduced, as a framework for objective performance evaluation of current and future dehazing tasks, through an extensive comparison of 15 single image de-hazing techniques over a vast range of image data sets. The proposed unified framework shows several advantages in evaluating diverse and perceptually meaningful image features but also in elucidating future directions for improvement in image dehazing tasks.INDEX TERMS haze, single image de-hazing, deep-learning, generative adversarial network (GAN), convolutional neural network, bench-marking, survey, computational-performance, computer vision, image processing.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

A Framework for Objective Evaluation of Single Image De-Hazing Techniques

Artusi

Raftopoulos

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…According to the research in [22], the images I − A/t k + A in equation ( 13) and I − A/J k − A + αt 0 /1 + α in equation ( 14) can both be considered as the denoising tasks whose noise levels are �� λ 1 /2 and �� λ 2 /2(1 + α) , respectively. erefore, any image denoiser can be solved by equations (18) and (19).…”

Section: Estimation Of Transmission Tmentioning

confidence: 99%

“…Chen et al [17] proposed a gated context aggregation network for image dehazing and deraining and applied the smoothed dilated convolution to avoid the gridding artifacts. Most CNN-based methods leverage haze-free images to synthesize hazy datasets [17,18]. However, some researchers thought that it could not represent the data distribution of real hazy images correctly, and some deficiencies existed in those models trained with synthesized datasets.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Enabled Variational Optimization Method for Image Dehazing in Maritime Intelligent Transportation Systems

Wang

Zhang

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Image dehazing has become a fundamental problem of common concern in computer vision-driven maritime intelligent transportation systems (ITS). The purpose of image dehazing is to reconstruct the latent haze-free image from its observed hazy version. It is well known that the accurate estimation of transmission map plays a vital role in image dehazing. In this work, the coarse transmission map is firstly estimated using a robust fusion-based strategy. A unified optimization framework is then proposed to estimate the refined transmission map and latent sharp image simultaneously. The resulting constrained minimization model is solved using a two-step optimization algorithm. To further enhance dehazing performance, the solutions of subproblems obtained in this optimization algorithm are equivalent to deep learning-based image denoising. Due to the powerful representation ability, the proposed method can accurately and robustly estimate the transmission map and latent sharp image. Numerous experiments on both synthetic and realistic datasets have been performed to compare our method with several state-of-the-art dehazing methods. Dehazing results have demonstrated the proposed method’s superior imaging performance in terms of both quantitative and qualitative evaluations. The enhanced imaging quality is beneficial for practical applications in maritime ITS, for example, vessel detection, recognition, and tracking.

show abstract

“…Their method was competitive on the restoration of image detail and color fidelity. Das and Dutta 23 proposed a fast deep multi‐patch hierarchical network to restore nonhomogeneous hazed images by aggregating features of multiple image patches from different spatial sections. Ancuti et al 24 focused on the dataset of images with nonhomogeneous hazy and the solutions in image dehazing, and they found that all methods utilized a CNN architecture are based on the skeleton of a U‐Net.…”

Section: Introductionmentioning

confidence: 99%

A desmoking algorithm for endoscopic images based on improved U‐Net model

Lin

Jiang

Pang

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

In laparoscopic surgery, the smoke generated by operations including electrocautery and laser ablation seriously degrades the quality of endoscopic images. It not only reduces the visibility of the surgery, leading to increased risk of surgery, but also affects the performance of image processing in computer‐assisted surgery such as segmentation, 3D reconstruction and tracking. Therefore, a desmoking algorithm is required to eliminate smoke in endoscopic images. In this article, we study a U‐Net model that can eliminate smoke of the laparoscopic image in real‐time and preserve the natural appearance of the organ surface. Our method is based on the improved U‐Net in which convolutional block attention module is used as an embedded guide mask of the decoder part. The laparoscopic image dataset is provided by the Hamlyn Center, and the Blender software is used to simulate various situations of smoke added to the laparoscopic image for training and testing. For the proposed method, the peak signal‐to‐noise ratio value is up to 29.27 and the structural similarity index is up to 0.945 over the test images. The experimental results demonstrate that the proposed method achieves a better performance than other six existing methods, which is applicable for real‐time endoscopic image processing.

show abstract

Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing

Cited by 57 publications

References 12 publications

A Framework for Objective Evaluation of Single Image De-Hazing Techniques

A Framework for Objective Evaluation of Single Image De-Hazing Techniques

Deep Learning-Enabled Variational Optimization Method for Image Dehazing in Maritime Intelligent Transportation Systems

A desmoking algorithm for endoscopic images based on improved U‐Net model

Contact Info

Product

Resources

About