Dual-Stream Complex-Valued Convolutional Network for Authentic Dehazed Image Quality Assessment

Tuxin Guan, Chaofeng Li, Yuhui Zheng, Xiao‐Jun Wu, Alan C. Bovik

Abstract

Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employed that exploits the advantages of complex-valued representations, achieving better generalization capability on perceptual feature learning than real-valued ones. To learn more discriminative features to analyze the perceptual quality of dehazed images, we design a dual-stream CV-CNN architecture. The dual-stream model comprises a distortion-sensitive stream that operates on the dehazed RGB image, and a haze-aware stream on a novel dark channel difference image. The distortion-sensitive stream accounts for perceptual distortion artifacts, while the haze-aware stream addresses the possible presence of residual haze. Experimental results on three publicly available dehazed image quality assessment (DQA) databases demonstrate the effectiveness and generalization of our proposed CV-CNN DQA model as compared to state-of-the-art no-reference image quality assessment algorithms.
BibTeX
@article{guan2024dual,
  author = {Tuxin Guan and Chaofeng Li and Yuhui Zheng and Xiao‐Jun Wu and Alan C. Bovik},
  title = {{Dual-Stream Complex-Valued Convolutional Network for Authentic Dehazed Image Quality Assessment}},
  journal = {IEEE Trans. Image Process.},
  year = {2024},
  doi = {10.1109/tip.2023.3343029},
}

Loading related content...

Figure