| 83 | 0 | 6 |
| Downloads | Citas | Reads |
To address the issue of performance degradation in advanced visual tasks, such as object detection, semantic segmentation, and person re-identification caused by complex degraded images under haze weather conditions, an overview of dehazing techniques for degraded images in complex scenes was provided. First, the formation mechanism of haze images and the degradation models were introduced. Second, the evolution from conventional physical model-based image dehazing methods to current deep learning-based approaches was reviewed, providing a detailed analysis of the characteristics, advantages, and limitations of each method. Finally, common datasets and evaluation metrics in the field were presented and future development trends were discussed to provide valuable references for researchers in related fields and jointly promote image dehazing technologies towards a more intelegent and practical direction.
[1]CHOW T Y,LEE K H,CHAN K L.Detection of targets in road scene images enhanced using conditional GAN-based dehazing model[J]. Applied Sciences,2023,13(9):5326.
[2]LEE S,SON T,KWAK S.FIFO:learning foginvariant features for foggy scene segmentation[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2022:18889-18899.
[3]FAN G D, GAN M, FAN B, et al. Multiscale cross-connected dehazing network with scene depth fusion[J]. IEEE Transactions on Neural Networks and Learning Systems,2024,35(2):1598-1612.
[4]DWIVEDI P,CHAKRABORTY S.A comprehensive qualitative and quantitative survey on image dehazing based on deep neural networks[J]. Neurocomputing,2024,610:128582.
[5]HE C M,SHEN Y Q,FANG C Y,et al.Diusion models in low-level vision:a survey[EB/OL].(2025-02-25)[2025-04-12]. https：//doi. org/10.48550/arxiv.2406.11138.
[6]LAN Y W,CUI Z G,SU Y Z,et al.SSKDN:a semisupervised knowledge distillation network for single image dehazing[J].Journal of Electronic Imaging,2023,32(1):013002.
[7]YANG X T,XU Z,LUO J B.Towards perceptual image dehazing by physics-based disentanglement and adversarial training[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2018,32(1):7485-7492.
[8]MCCARTNEY E J,HALL F F J.Optics of the atmosphere:scattering by molecules and particles[J].Physics Today,1977,30(5):76-77.
[9]NAYAR S K, NARASIMHAN S G. Vision in bad weather[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2002:820-827.
[10]王道累，张天宇．图像去雾算法的综述及分析[J]．图形学报，2020,41(6):861-870.WANG D L,ZHANG T Y.Review and analysis of image defogging algorithm[J].Journal of Graphics,2020,41(6):861-870.
[11]KIM T K,PAIK J K,KANG B S.Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering[J]. IEEE Transactions on Consumer Electronics,1998,44(1):82-87.
[12]ZUIDERVELD K.Contrast limited adaptive histogram equalization[M]//Andrew S G.Graphics Gems.Amsterdam:Elsevier,1994:474-485.
[13]ZHANG H, LIU X, HUANG Z T, et al. Single image dehazing based on fast wavelet transform with weighted image fusion[C]//2014 IEEE International Conference on Image Processing(ICIP).Piscataway,NJ,USA:IEEE,2014:4542-4546.
[14]张登银，鞠铭烨，钱雯．图像去雾算法研究现状与展望[J]．南京邮电大学学报（自然科学版），2020,40(5):101-111.ZHANG D Y, JU M Y, QIAN W. Research status and prospect of image dehazing algorithm[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition), 2020,40(5):101-111.
[15]JOBSON D J, RAHMAN Z, WOODELL G A.Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing,1997,6(3):451-462.
[16]JOBSON D J, RAHMAN Z, WOODELL G A.A multiscale retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing,1997,6(7):965-976.
[17]OAKLEY J P,SATHERLEY B L.Improving image quality in poor visibility conditions using a physical model for contrast degradation[J].IEEE Transactions on Image Processing,1998,7(2):167-179.
[18]张然．基于分数阶偏微分方程的雾天图像增强算法[D]．西安：西安理工大学，2018:21-27.ZHANG R. Hazy image enhancement algorithm based on fractional partial differential equations[D].Xi’an:Xi’an University of Technology, 2018:21-27.
[19]周理，毕笃彦，何林远．融合变分偏微分方程的单幅彩色图像去雾[J]．光学精密工程，2015,23(5):1466-1473.ZHOU L,BI D Y,HE L Y.Single color image dehazing using variational partial differential equation[J]. Optics and Precision Engineering, 2015, 23(5):1466-1473.
[20]HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[C]//2009IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2009:1956-1963.
[21]ZHU Q S, MAI J M, SHAO L. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing,2015,24(11):3522-3533.
[22]FATTAL R.Dehazing using color-lines[J].ACM Transactions on Graphics,2014,34(1):1-14.
[23]BERMAN D,TREIBITZ T,AVIDAN S.Nonlocal image dehazing[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2016:1674-1682.
[24]CAI B L, XU X M, JIA K, et al. DehazeNet:an end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198.
[25]REN W Q,PAN J S,ZHANG H,et al.Single image dehazing via multi-scale convolutional neural networks with holistic edges[J]. International Journal of Computer Vision,2020,128(1):240-259.
[26]LI Y N, MIAO Q G, OUYANG W L, et al.LAP-Net:level-aware progressive network for image dehazing[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV). Piscataway,NJ,USA:IEEE,2019:3275-3284.
[27]ZHANG H,PATEL V M.Densely connected pyramid dehazing network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2018:3194-3203.
[28]LI B Y,PENG X L,WANG Z Y,et al.AODNet:all-in-one dehazing network[C]//2017 IEEE International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2017:4780-4788.
[29]REN W Q,MA L,ZHANG J W,et al.Gated fusion network for single image dehazing[C]//2018IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2018:3253-3261.
[30]QIN X,WANG Z L,BAI Y C,et al.FFA-Net:feature fusion attention network for single image dehazing[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):11908-11915.
[31]CHEN D D,HE M M,FAN Q N,et al.Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision(WACV). Piscataway,NJ,USA:IEEE,2019:1375-1383.
[32]LIU X H,MA Y R,SHI Z H,et al.GridDehazeNet:attention-based multi-scale network for image dehazing[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2019:7313-7322.
[33]DONG H, PAN J S, XIANG L, et al. Multiscale boosted dehazing network with dense feature fusion[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2020:2154-2164.
[34]RONNEBERGER O,FISCHER P,BROX T.UNet:convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.Cham:Springer International Publishing,2015:234-241.
[35]GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J].Communications of the ACM,2020,63(11):139-144.
[36]QU Y Y,CHEN Y Z,HUANG J Y,et al.Enhanced pix2pix dehazing network[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2019:8152-8160.
[37]WU H Y,QU Y Y,LIN S H,et al.Contrastive learning for compact single image dehazing[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2021:10546-10555.
[38]PENG Z, LUO M N, HUANG W B, et al.Learning representations by graphical mutual information estimation and maximization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(1):722-737.
[39]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An image is worth 16×16 words:transformers for image recognition at scale[EB/OL].(2021-06-03)[2025-04-12]. https：//doi.org/10.48550/arxiv.2010.11929.
[40]SONG Y D, HE Z Q, QIAN H, et al. Vision transformers for single image dehazing[J]. IEEE Transactions on Image Processing,2023,32:1927-1941.
[41]GUO C L,YAN Q X,ANWAR S,et al.Image dehazing transformer with transmission-aware3D position embedding[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2022:5802-5810.
[42]QIU Y W, ZHANG K H, WANG C X,et al.MB-TaylorFormer:multi-branch efficient transformer expanded by Taylor formula for image dehazing[C]//2023 IEEE/CVF International Conference on Computer Vision(ICCV).Piscataway,NJ,USA:IEEE,2023:12756-12767.
[43]CHEN Z Y,WANG Y C,YANG Y,et al.PSD:principled synthetic-to-real dehazing guided by physical priors[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2021:7176-7185.
[44]ZHAO S Y, ZHANG L, SHEN Y, et al. RefineDNet:a weakly supervised refinement framework for single image dehazing[J]. IEEE Transactions on Image Processing,2021,30:3391-3404.
[45]LI L,DONG Y L,REN W Q,et al.Semi-supervised image dehazing[J]. IEEE Transactions on Image Processing,2019,29:2766-2779.
[46]SHAO Y J, LI L, REN W Q, et al. Domain adaptation for image dehazing[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA:IEEE,2020:2805-2814.
[47]WANG Z Z, ZHAO H T, PENG J C, et al.ODCR:orthogonal decoupling contrastive regularization for unpaired image dehazing[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ, USA:IEEE,2024:25479-25489.
[48]ENGIN D,GENC A,EKENEL H K.Cycle-dehaze:enhanced CycleGAN for single image dehazing[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Piscataway,NJ,USA:IEEE,2018:938-946.
[49]ZHU J Y,PARK T,ISOLA P,et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//2017 IEEE International Conference on Computer Vision(ICCV). Piscataway,NJ,USA:IEEE,2017:2242-2251.
[50]YANG Y,WANG C Y,LIU R S,et al.Selfaugmented unpaired image dehazing via density and depth decomposition[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA:IEEE, 2022:2027-2036.
[51]LI B Y, REN W Q, FU D P, et al. Benchmarking single image dehazing and beyond[J].IEEE Transactions on Image Processing,2018,28(1):492-505.
[52]ZHANG Y F,DING L,SHARMA G.HazeRD:an outdoor scene dataset and benchmark for single image dehazing[C]//2017 IEEE International Conference on Image Processing(ICIP). Piscataway,NJ,USA:IEEE,2017:3205-3209.
[53]ANCUTI C,ANCUTI C O,DE VLEESCHOUWER C. D-HAZY:a dataset to evaluate quantitatively dehazing algorithms[C]//2016 IEEE International Conference on Image Processing(ICIP).Piscataway,NJ,USA:IEEE,2016:2226-2230.
[54]ANCUTI C, ANCUTI C O, TIMOFTE R, et al.I-HAZE:a dehazing benchmark with real hazy and haze-free indoor images[M]//Advanced Concepts for Intelligent Vision Systems.Cham:Springer International Publishing,2018:620-631.
[55]ANCUTI C O,ANCUTI C,TIMOFTE R,et al.O-HAZE:a dehazing benchmark with real hazy and haze-free outdoor images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Salt Lake City:IEEE,2018:754.
[56]WANG Z, BOVIK A C, SHEIKH H R, et al.Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612.
[57]KANG Y M, ZHANG L, HU P, et al. Learning depth aware decomposition for single image dehazing[J]. Computer Vision and Image Understanding,2024,248:104069.
[58]LAN Y W,CUI Z G,LIU C,et al.Exploiting diusion prior for real-world image dehazing with unpaired training[J]. Proceedings of the AAAI Conference on Artificial Intelligence.2025,39(4):4455-4463.
[59]SINDAGI V A, OZA P, YASARLA R, et al.Prior-based domain adaptive object detection for hazy and rainy conditions[M]//Computer VisionECCV 2020. Cham:Springer International Publishing,2020:763-780.
[60]CHEN H T,WANG Y H,GUO T Y,et al.Pretrained image processing transformer[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway,NJ,USA:IEEE,2021:12294-12305.
[61]ZHOU H Y, JIANG F, LU H T. SSDA-YOLO:semi-supervised domain adaptive YOLO for cross-domain object detection[J]. Computer Vision and Image Understanding,2023,229:103649.
Basic Information:
DOI：10.20189/j.cnki.CN/61-1527/E.202601006
China Classification Code:TP391.41
Citation Information:
[1]LI Qinghui,CUI Zhigao,CHEN Yuqiang ,et al.Review on Dehazing Algorithm for Degraded Images in Complex Scenes[J].Journal of Rocket Force University of Engineering,2026,40(01):56-67.DOI:10.20189/j.cnki.CN/61-1527/E.202601006.
Fund Information:
陕西省自然科学基金面上项目(2023-JC-YB-501)