Image dehazing with hybrid total variation–L0 regularization

Dong, Wende; Xu, Xiangmin; Zhu, Chenlong; Hu, Luqi; Xu, Guili; Tao, Shuyin

doi:10.1117/1.jei.31.6.063014

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The author 16 proposes a surface-aware regularization method which is based on the surface area and L0-norm constraint. In reference 17 , the TV regularization is combined with the L0-norm regularization to form a novel hybrid regularization term, it is successfully used in image dehazing.…”

Section: Introductionmentioning

confidence: 99%

Hybrid total variation and L0-norm regularized non-blind deconvolution for Poissonian blurred image restoration

Zhu,

Yang,

Dong

2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Imaging Systems

View full text Add to dashboard Cite

In the fields of astronomical observation and fluorescence microscopic imaging, the obtained image is usually degraded by blur effects and Poisson noise. In this paper, we propose a robust hybrid regularization method consisting of total variation and L0-norm of image gradients and combine it with the Poisson distribution to formulate this kind of ill-posed problem. We also propose an efficient alternately minimization algorithm based on variable splitting and Lagrange multipliers to find the optimal solution, which can transform the original problem into a regularized deconvolution problem with quadratic fidelity term and a simple convex optimization problem. In the end, we carry out experiments to prove its convergence and effectiveness, the results show that the proposed method is stable, efficient and the quality of the restored image is comparable with some state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%