Real-world dehazing method with invariant learning

被引：0
|
作者：
Meng X. [1 ]
Feng Y. [1 ]
Su Z. [1 ]
Zhou F. [1 ]
机构：
[1] School of Computer Science and Engineering, Research Institute of Sun Yat-sen University in Shenzhen, Sun Yat-sen University, Guangzhou
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2024年 / 58卷 / 02期
关键词：
feature correlation; image dehazing; invariant learning; quality interference;
D O I：
10.3785/j.issn.1008-973X.2024.02.005
中图分类号：
学科分类号：
摘要：
A real hazy image removal method based on invariant learning was proposed to solve the problem of quality interference in image dehazing. The Fourier feature transform was used to linearize the features extracted by the network. Then global weighting was performed and covariance was solved for the linearized features. The correlation between the features was removed. Invariant learning makes the network more concerned about the essential relationship between features and the dehazing image, which can enable the network to obtain stable cross-domain features. The different roles of the data and the proposed method were analyzed and explained. The improvement of the atmospheric scattering model was realized, and a new dataset suitable for real haze scenarios was constructed. The real-world dehazing effect of the method was verified through extensive experiments. © 2024 Zhejiang University. All rights reserved.
引用
收藏
页码：268 / 278
页数：10
相关论文
共 34 条
  • [1] ARYAN M, MURARI M, PRATIK N, Et al., ReViewNet: a fast and resource optimized network for enabling safe autonomous driving in hazy weather conditions [J], IEEE Transactions on Intelligent Transportation Systems, 22, pp. 4256-4266, (2021)
  • [2] CAO Z, QIN Y, JIA L, Et al., Haze removal of railway monitoring images using multi-scale residual network [J], IEEE Transactions on Intelligent Transportation Systems, 22, 12, pp. 7460-7473, (2020)
  • [3] BAI H, PAN J, XIANG X, Et al., Self-guided image dehazing using progressive feature fusion [J], IEEE Transactions on Image Processing, 31, pp. 1217-1229, (2022)
  • [4] WU H, QU Y, LIN S, Et al., Contrastive learning for compact single image dehazing, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10551-10560, (2021)
  • [5] LI H, LI J, ZHAO D, Et al., Dehazeflow: multi-scale conditional flow network for single image dehazing, Proceedings of the 29th ACM International Conference on Multimedia, pp. 2577-2585, (2021)
  • [6] QIN X, WANG Z, BAI Y, Et al., FFA-Net: feature fusion attention network for single image dehazing, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11908-11915, (2020)
  • [7] MA L, MA T, LIU R, Et al., Toward fast, flexible, and robust low-light image enhancement, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5637-5646, (2022)
  • [8] ARJOVSKY M, BOTTOU L, GULRAJANI I, Et al., Invariant risk minimization
  • [9] WANG J, LAN C, LIU C, Et al., Generalizing to unseen domains: a survey on domain generalization [J], IEEE Transactions on Knowledge and Data Engineering, 35, 8, pp. 8052-8072, (2023)
  • [10] MUANDET K, BALDUZZI D, SCHOLKOPF B., Domain generalization via invariant feature representation, International Conference on Machine Learning, pp. 10-18, (2013)
1234