Multi-Purpose Oriented Single Nighttime Image Haze Removal Based on Unified Variational Retinex Model
The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Abstract
Under the nighttime haze environment, the quality of acquired images will be deteriorated significantly owing to the influences of multiple adverse degradation factors. In this paper, we develop a multi-purpose oriented haze removal framework focusing on nighttime hazy images. First, we construct a nonlinear model based on the classic Retinex theory to formulate multiple adverse degradations of a nighttime hazy image. Then, a novel variational Retinex model is presented to simultaneously estimate a smoothed illumination component and a detail-revealed reflectance component and predict the noise map from a pre-processed nighttime hazy image in a unified manner. Specifically, an${\ell _{0}}$norm is imposed on the reflectance to reveal the structural details and we make use of$\ell _{1}$norm to constrain the piece-wise smoothness of the illumination and apply${\ell _{2}}$norm to enforce the total intensity of the noise map. Afterwards, the haze in the illumination component is removed based on prior-based dehazing method and the contrast of the reflectance component is improved in the gradient domain. Finally, we combine the dehazed illumination and the improved reflectance to generate the haze-free image. Experiments show that our proposed framework performs better than famous nighttime image dehazing methods both in visual effects and objective comparisons. In addition, the proposed framework can also be applicable to other types of degraded images.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 1×
“Furthermore, widely used full-reference indicators dubbed as PSNR and SSIM [53], are used to evaluate the dehazed results in Fig.”
MethodBoyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.120 · Cited by 9,201 · cited 1×
“Specifically, given a clear image, semantic labels and depth map, 3R [23] first employs the SLIC [51] technique to divide the semantic label into superpixels and makes use of the coordinates transformation to reconstruct the scene geometry.”
MethodSingle image haze removal using dark channel prior
He, K., Sun, J., & Tang, X. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.168 · Cited by 7,601
He, K., Sun, J., & Tang, X. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.213 · Cited by 5,546
Land, E. H., & McCann, J. J. (1971) · Journal of the Optical Society of America · doi:10.1364/josa.61.000001 · Cited by 4,095 · cited 2×
“Concretely, inspired by Retinex theory [25], [26], a modified Retinex model comprising four components: reflectance, illumination, glow and noise is first defined to illustrate the formation and composition of a nighttime hazy image.”
MethodDehazeNet: An End-to-End System for Single Image Haze Removal
Cai, B., Xu, X., Jia, K., Qing, C., & Tao, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2598681 · Cited by 3,367 · cited 4×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodInfluentialLIME: Low-Light Image Enhancement via Illumination Map Estimation
Guo, X., Li, Y., & Ling, H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2639450 · Cited by 2,998 · cited 5×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialSelf-citationThe Retinex Theory of Color Vision
Land, E. H. (1977) · Scientific American · doi:10.1038/scientificamerican1277-108 · Cited by 2,981 · cited 2×
“Concretely, inspired by Retinex theory [25], [26], a modified Retinex model comprising four components: reflectance, illumination, glow and noise is first defined to illustrate the formation and composition of a nighttime hazy image.”
MethodA Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior
Zhu, Q., Mai, J., & Shao, L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2446191 · Cited by 2,469 · cited 4×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodInfluentialAOD-Net: All-in-One Dehazing Network
Li, B., Peng, X., Wang, Z., Xu, J., & Feng, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.511 · Cited by 2,342 · cited 1×
“AOD-Net [33] is developed to generate the clean image based on a reformulated atmospheric scattering model and a designed light-weight CNN.”
MethodVisibility in bad weather from a single image
Tan, R. T. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587643 · Cited by 2,280 · cited 1×
“Tan [30] maximizes the contrast of hazy images to remove the haze based on the observation that the visibility of clear images is better than that of hazy images.”
BackgroundSingle Image Dehazing via Multi-scale Convolutional Neural Networks
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., & Yang, M.-H. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_10 · Cited by 1,759 · cited 5×
“…including prior-based dehazing methods (e.g. DCP [1], CAP [2], CEP [3] and RLP [6]), learning-based dehazing methods (e.g. DehazeNet [11], MSCNN [12], PDN [13] and PSD [14]) and variational-based dehazing methods (e.g. BCCR [7], GRM [8], EVID [9] and FVID [10]), are unable to remove the…”
BackgroundMethodInfluentialContrast restoration of weather degraded images
Narasimhan, S. G., & Nayar, S. K. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1201821 · Cited by 1,642 · cited 1×
“In the early stage, researchers adopt multiple image [27], depth-based models [28] and polarization-based methods [29] to yield pleasant haze-free results.”
BackgroundLambertian reflectance and linear subspaces
Basri, R., & Jacobs, D. W. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1177153 · Cited by 1,576
Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model
Li, M., Liu, J., Yang, W., Sun, X., & Guo, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2810539 · Cited by 1,245 · cited 6×
“To prove the validity of our proposed unified model, we consider the variational structure-revealing (SR) Retinex model [59] to replace our proposed unified model and meanwhile other operations of the nighttime haze removal framework remain unchanged.”
BackgroundMethodInfluentialFattal, R. (2014) · ACM Transactions on Graphics · doi:10.1145/2651362 · Cited by 1,167 · cited 1×
“Similarly, from the statistical observation and analysis on a large amount of outdoor images, several powerful priors are developed to restore clear images, such as CEP [3], MPC [5], color-lines [31], haze-lines [32], RLP [6] and more.”
BackgroundEfficient Image Dehazing with Boundary Constraint and Contextual Regularization
Meng, G., Wang, Y., Duan, J., Xiang, S., & Pan, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.82 · Cited by 1,164 · cited 6×
“BCCR [7], GRM [8], EVID [9] and FVID [10]), are unable to remove the nighttime haze well.”
BackgroundInfluentialA Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation
Fu, X., Zeng, D., Huang, Y., Zhang, X.-P., & Ding, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.304 · Cited by 1,081 · cited 10×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialImage smoothing via L0gradient minimization
Xu, L., Lu, C., Xu, Y., & Jia, J. (2011) · ACM Transactions on Graphics · doi:10.1145/2070781.2024208 · Cited by 786
Deep photo: model-based photograph enhancement and viewing
Kopf, J., Neubert, B., Chen, B., Cohen, M., Cohen-Or, D., Deussen, O., Uyttendaele, M., & Lischinski, D. (2008) · ACM Transactions on Graphics · doi:10.1145/1409060.1409069 · Cited by 713
Polarization-based vision through haze
Schechner, Y. Y., Narasimhan, S. G., & Nayar, S. K. (2003) · Applied Optics · doi:10.1364/ao.42.000511 · Cited by 687 · cited 1×
“based models [28] and polarization-based methods [29] to yield pleasant haze-free results.”
Fu, X., Liao, Y., Zeng, D., Huang, Y., Zhang, X.-P., & Ding, X. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2474701 · Cited by 467 · cited 9×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialDabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007) · 2007 IEEE International Conference on Image Processing · doi:10.1109/icip.2007.4378954 · Cited by 458 · cited 3×
“(a) is the input image; (b)-(k) are the dehazed results of NDIM [16], GS [17], MRP [18], FMRP [18], PWAB [21], OSFD [23], FDGCN [24], GHLP [40], VNID [50] and DPMF [42] with a post-processing performed using CBM3D [54] with the denoising parameter σ=30; (l) is the result provided by our proposed method without post-pr…”
MethodResultLR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model
Ren, X., Yang, W., Cheng, W.-H., & Liu, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2984098 · Cited by 405 · cited 7×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialPSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
Chen, Z., Wang, Y., Yang, Y., & Liu, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00710 · Cited by 370 · cited 6×
“PSD [14], TMS-GAN [35] and more, are presented to realize the translation from the hazy to the clear in an end-to-end pattern.”
BackgroundMethodInfluentialSingle Image Dehazing Using Haze-Lines
Berman, D., Treibitz, T., & Avidan, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2882478 · Cited by 329 · cited 1×
“Similarly, from the statistical observation and analysis on a large amount of outdoor images, several powerful priors are developed to restore clear images, such as CEP [3], MPC [5], color-lines [31], haze-lines [32], RLP [6] and more.”
BackgroundProximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing
Yang, D., & Sun, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_43 · Cited by 315 · cited 3×
“…prior-based dehazing methods (e.g. DCP [1], CAP [2], CEP [3] and RLP [6]), learning-based dehazing methods (e.g. DehazeNet [11], MSCNN [12], PDN [13] and PSD [14]) and variational-based dehazing methods (e.g. BCCR [7], GRM [8], EVID [9] and FVID [10]), are unable to remove the nighttime haze…”
BackgroundMethodSTAR: A Structure and Texture Aware Retinex Model
Xu, J., Hou, Y., Ren, D., Liu, L., Zhu, F., Yu, M., Wang, H., & Shao, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2974060 · Cited by 315 · cited 5×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialA Joint Intrinsic-Extrinsic Prior Model for Retinex
Cai, B., Xu, X., Guo, K., Jia, K., Hu, B., & Tao, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.431 · Cited by 289 · cited 8×
“Besides, the synthetic dataset NHM is also tested for quantitatively comparing previous Retinex models [55], [56], [57], [58], [59], [60], [61] with our model and the average PSNR and SSIM values of the NHM are revealed in Table III.”
BackgroundMethodInfluentialNighttime Haze Removal with Glow and Multiple Light Colors
Li, Y., Tan, R. T., & Brown, M. S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.34 · Cited by 268 · cited 10×
“In addition, some new imaging models [16], [17] and prior knowledge [18] are proposed to explain the degradation features of nighttime hazy scenes for nighttime haze removal.”
BackgroundMethodInfluentialSelf-citationSingle Image Dehazing Using Color Ellipsoid Prior
Bui, T. M., & Kim, W. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2771158 · Cited by 247 · cited 4×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodInfluentialRobust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization
Chen, C., Do, M. N., & Wang, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_36 · Cited by 245 · cited 5×
“Chen et al. [8] first make use of the total generalized variation (TGV) to devise a depth-aware approach to optimize the scene transmission and then develop the gradient residual minimization (GRM) constraint to restore the haze-free image.”
BackgroundMethodInfluentialFast Haze Removal for Nighttime Image Using Maximum Reflectance Prior
Zhang, J., Cao, Y., Fang, S., Kang, Y., & Chen, C. W. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.742 · Cited by 201 · cited 14×
“In addition, some new imaging models [16], [17] and prior knowledge [18] are proposed to explain the degradation features of nighttime hazy scenes for nighttime haze removal.”
BackgroundMethodInfluentialNighttime Dehazing with a Synthetic Benchmark
Zhang, J., Cao, Y. H., Zha, Z.-J., & Tao, D. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413763 · Cited by 197 · cited 10×
“In [23], a simple network architecture based on encoder-decoder structure is devised to provide the end-to-end mapping relationship from a nighttime hazy image to a clear result.”
BackgroundMethodInfluentialNighttime haze removal using color transfer pre-processing and Dark Channel Prior
Pei, S., & Lee, T.-Y. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467020 · Cited by 171 · cited 2×
“Pei and Lee [15] propose a two-stage nighttime dehazing method: airlight color transfer and haze removal using the daytime restoration strategy.”
MethodNighttime haze removal based on a new imaging model
Zhang, J., Cao, Y. H., & Wang, Z. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025924 · Cited by 167 · cited 10×
“In addition, some new imaging models [16], [17] and prior knowledge [18] are proposed to explain the degradation features of nighttime hazy scenes for nighttime haze removal.”
BackgroundMethodResultInfluentialMulti-Level Fusion and Attention-Guided CNN for Image Dehazing
Zhang, X., Wang, T., Luo, W., & Huang, P. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3046625 · Cited by 164 · cited 1×
“…[33] is developed to generate the clean image based on a reformulated atmospheric scattering model and a designed light-weight CNN. Zhang et al. [34] present a multi-level fusion module which makes use of both low-level and high-level features and a residual attention based CNN module for image…”
BackgroundA Hybrid l1-l0 Layer Decomposition Model for Tone Mapping
Liang, Z., Xu, J., Zhang, D. D., Cao, Z., & Zhang, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00500 · Cited by 158 · cited 1×
“…= sign ( x ) max ( | x | − ω, 0 ) . e) T 1 sub-problem: The optimization function with respect to T 1 is : According to previous strategies [45], [47], the above objec-tive function (18) can be solved in an element-wise manner and the solution of T 1 is expressed using a piecewise function :…”
MethodAncuti, C., Ancuti, C. O., De Vleeschouwer, C., & Bovik, A. C. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532760 · Cited by 136 · cited 2×
“Based on the image fusion strategy, some works [19], [20], [21] leverage the fusion approaches to achieve haze-free images, whereas these fusion-based methods Fig.”
MethodFusion-based Variational Image Dehazing
Galdrán, A., Vázquez-Corral, J., Pardo, D., & Bertalmío, M. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2643168 · Cited by 134 · cited 6×
“In [10], a fusion based variational image dehazing (FVID)”
BackgroundInfluentialIDRLP: Image Dehazing Using Region Line Prior
Ju, M., Ding, C., Guo, C. A., Ren, W., & Tao, D. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3122088 · Cited by 124 · cited 4×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodInfluentialEnhanced Variational Image Dehazing
Galdrán, A., Vázquez-Corral, J., Pardo, D., & Bertalmío, M. (2015) · SIAM Journal on Imaging Sciences · doi:10.1137/15m1008889 · Cited by 113 · cited 5×
“…dehazing methods (e.g. DehazeNet [11], MSCNN [12], PDN [13] and PSD [14]) and variational-based dehazing methods (e.g. BCCR [7], GRM [8], EVID [9] and FVID [10]), are unable to remove the nighttime haze well. are incapable of dealing with glow and halo effects owing to the lack of physical…”
BackgroundMethodInfluentialSingle Image Dehazing With Depth-Aware Non-Local Total Variation Regularization
Liu, Q., Gao, X., He, L., & Lu, W. B. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2849928 · Cited by 106 · cited 1×
“Liu et al. [36] develop a non-local total variation (NLTV) regularization for better maintaining depth edges.”
BackgroundMulti-path dilated convolution network for haze and glow removal in nighttime images
Kuanar, S. P., Mahapatra, D., Bilas, M., & Rao, K. R. (2021) · The Visual Computer · doi:10.1007/s00371-021-02071-z · Cited by 105 · cited 1×
“DeGlow-Dehaze network [43] is devised to remove the glow effects.”
BackgroundDay and Night-Time Dehazing by Local Airlight Estimation
Ancuți, C., Ancuti, C. O., Vleeschouwer, C. D., & Bovik, A. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2988203 · Cited by 104 · cited 1×
“In [41], the airlight is estimated locally by using multiple patch sizes.”
MethodNighttime Single Image Dehazing via Pixel-Wise Alpha Blending
Yu, T., Song, K., Miao, P., Yang, G., Yang, H., & Chen, C. (2019) · IEEE Access · doi:10.1109/access.2019.2936049 · Cited by 97 · cited 10×
“A pixel-based alpha fusion strategy is designed by Yu et al. [21] to estimate the parameters of the physical model.”
BackgroundMethodResultInfluentialNighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks
Yan, W., Tan, R. T., & Dai, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58610-2_28 · Cited by 80
Single image haze removal based on the improved atmospheric scattering model
Ju, M., Gu, Z., & Zhang, D. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.04.034 · Cited by 77 · cited 2×
“…as follows : where R ( x ) and L ( x ) respectively stand for the reflectance and the illumination component of the image I lo w − light ( x ) , in which the illumination component is degraded by the hazes because the hazes are usually distributed in the low frequency part of the hazy image [44].”
BackgroundVariational Single Nighttime Image Haze Removal With a Gray Haze-Line Prior
Wang, W., Wang, A., & Liu, C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3141252 · Cited by 76 · cited 10×
“[16], GS [17], MRP [18], FMRP [18], PWAB [21], OSFD [23], FDGCN [24], GHLP [40], VNID [50] and DPMF [42] with a post-processing performed using CBM3D [54] with the denoising parameter σ = 30; (l) is the result provided by our proposed method without post-processing.”
BackgroundMethodResultInfluentialTMS-GAN: A Twofold Multi-Scale Generative Adversarial Network for Single Image Dehazing
Wang, P., Zhu, H., Huang, H., Zhang, H., & Wang, N. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3097713 · Cited by 72 · cited 1×
“After that, many effective haze removal networks, such as PSD [14], TMS-GAN [35] and more, are presented to realize the translation from the hazy to the clear in an end-to-end pattern.”
Nighttime Image Dehazing Based on Variational Decomposition Model
Liu, Y., Yan, Z., Wu, A., Tian, Y., & Li, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00079 · Cited by 63 · cited 2×
“Similar to [38], [39], for non-uniform light sources, we assume that the atmospheric light is a local constant rather than a global constant and employ the modified physical model : where the spatially varying atmospheric light A ( x ) is locally calculated based on He’s method [1] and the…”
MethodSelf-citationVariational Single Image Dehazing for Enhanced Visualization
Fang, F., Wang, T., Wang, Y., Zeng, T., & Zhang, G. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2958755 · Cited by 56 · cited 1×
“Fang et al. [37] reformulate the physical model and construct a variational model containing two regularization terms for haze removal.”
MethodSingle nighttime image dehazing based on image decomposition
Liu, Y., Wang, A., Zhou, H. Y., & Jia, P. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.107986 · Cited by 51 · cited 4×
“Similar to [38], [39], for non-uniform light sources, we assume that the atmospheric light is a local constant rather than a global constant and employ the modified physical model : where the spatially varying atmospheric light A ( x ) is locally calculated based on He’s method [1] and the…”
BackgroundMethodInfluentialSelf-citationBDPK: Bayesian Dehazing Using Prior Knowledge
Ju, M., Ding, C., Zhang, D., & Guo, Y. J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2869594 · Cited by 50 · cited 2×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodSingle image dehazing via multi‐scale gradient domain contrast enhancement
Mi, Z., Zhou, H., Zheng, Y., et al. (2015) · IET Image Processing · doi:10.1049/iet-ipr.2015.0112 · Cited by 48 · cited 1×
“Similar to the gradient operations [38], [49], we manipulate the gradients of the reflectance ∇ R by dividing the transmission t ( x ) to enhance the details.”
MethodIDBP: Image Dehazing Using Blended Priors Including Non-Local, Local, and Global Priors
Ju, M., Ding, C., Ren, W., et al. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3101503 · Cited by 29 · cited 3×
“On the basis of the widely used haze imaging model [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] in the community of image processing, the hazy image I ( x ) can be illustrated as follows : where t ( x ) is the medium transmission, A denotes the atmospheric light and J (…”
BackgroundMethodYang, C.-H., Lin, Y.-H., & Lu, Y.-C. (2022) · IEEE Access · doi:10.1109/access.2022.3173330 · Cited by 21 · cited 8×
“[50] design a variation-based nighttime image dehazing (VNID) method to restore the clear image based on a illumination estimator and a luminance-guided coloring model.”
MethodResultInfluentialNighttime Haze Removal with Glow Decomposition Using GAN
Koo, B., & Kim, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-41404-7_57 · Cited by 20 · cited 2×
“More recently, several dehazing networks [22], [23], [24] are devised to provide the end-to-end mapping between a nighttime hazy image and a haze-free result.”
BackgroundNighttime image dehazing using color cast removal and dual path multi-scale fusion strategy
Wang, B., Li, H., Wei, B., Kang, Z., & Li, C. (2021) · Frontiers of Computer Science · doi:10.1007/s11704-021-0162-x · Cited by 12 · cited 10×
“For synthetic nighttime hazy scenes, NDIM [16], MRP [18], FMRP [18], PWAB [21] OSFD [23], FDGCN [24] and DPMF [42] are prone to be influenced by the glow effects, which results in apparent uneven illumination in the dehazed results (see in the sixth row of Fig.”
BackgroundMethodResultInfluentialA Visibility-Guided Fusion Framework for Fast Nighttime Image Dehazing
Luó, X., Guo, Y., Ewurum, H. C., et al. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03398-9_41 · Cited by 3 · cited 2×
“[20] develop a nighttime haze removal approach”
Background
Metadata
- Authors
- Liu, Y., Yan, Z., Tan, J., & Li, Y.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2023-04
- Volume
- 33
- Issue
- 4
- Pages
- 1643-1657
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4313026854
- Cited by
- 190
- References
- 61
- FWCI
- 12.63
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.