Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition

Yang, Yang; Wang, Chaoyue; Liu, Risheng; Zhang, Lin; Guo, Xiaojie; Tao, Dacheng

doi:10.1109/cvpr52688.2022.00208

Cited by 128 publications

(72 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result by Zhu et al [19] suffers from a loss of dark details owing to excessive haze removal. The remaining six deeplearning-based methods perform relatively well, in which results by Cai et al [21] and Yang et al [28] are more favorable than others. Our result, as expected, exhibits three desirable outcomes: haze removal, sharpness enhancement, and color gamut expansion.…”

Section: Resultsmentioning

confidence: 88%

“…As a result, it can be concluded that the proposed method demonstrates a comparative performance with state-of-theart benchmark methods, notably the deep learning models of Yang et al [28], Ren et al [3], and Dong et al [26].…”

Section: B Quantitative Evaluation On Public Datasetsmentioning

confidence: 89%

“…This interpretation can be further supported by the unimpressive score of the unsupervised model of Li et al [27], which does not require ground-truth references. However, this and the best-performing model of Yang et al [28] have shown the great potential of unsuper-vised and unpaired learning in computer vision.…”

Section: B Quantitative Evaluation On Public Datasetsmentioning

confidence: 90%

“…The D-HAZY is generated from the Middlebury [49] and NYU Depth [50] datasets according to the degradation model in (7) Tables 2 and 3 demonstrate average evaluation scores in FSIMc and TMQI on five public datasets. It can be observed from Table 2 that the proposed method is ranked fourth overall, below the deep dehazing models of Yang et al [28], Ren et al [3], and Dong et al [26]. However, it is worth noting that the difference between its FSIMc score and the best is subtle.…”

Section: B Quantitative Evaluation On Public Datasetsmentioning

confidence: 95%

“…Some state-of-the-art deep dehazing networks developed recently include GridDehazeNet (GDN) [25], multi-scale boosted dehazing network (MSBD) [26], you only look yourself (YOLY) [27], and self-augmented unpaired image dehazing (D 4 ) [28]. GDN is a supervised network and comprises three modules.…”

Section: Deep Learningmentioning

confidence: 99%

See 4 more Smart Citations

Singe Image Dehazing With Unsharp Masking and Color Gamut Expansion

Ngo¹,

Lee

Kang

2022

IEEE Access

View full text Add to dashboard Cite

Image dehazing is a fundamental problem in computer vision and has hitherto engendered prodigious amounts of studies. Recently, with the well-recognized success of deep learning techniques, this field has been dominated by deep dehazing models. However, deep learning is not always a panacea, especially for the practicalities of image dehazing, because high computational complexity, expensive maintenance costs, and high carbon emission are three noticeable problems. Computational efficiency is, therefore, a decisive factor in real-world circumstances. To cope with this growing demand, we propose a linear time algorithm tailored to three primitive parts: unsharp masking (pre-processing), dehazing, and color gamut expansion (post-processing). The first enhances the sharpness according to the local variance of image intensities. The second removes haze based on the improved color attenuation prior, and the third addresses a residual effect of color gamut reduction. Extensive experimental results demonstrated that the proposed method performed comparatively with popular benchmarks, notably deep dehazing models. With such a comparative performance, the proposed method is still fast and efficient, favoring real-world computer vision systems.INDEX TERMS Image dehazing, unsharp masking, color gamut expansion, linear time complexity

show abstract

Section: Resultsmentioning

confidence: 88%