Multi-Scale Deep Residual Learning-Based Single Image Haze Removal via Image Decomposition

Chia Hung Yeh, Chih Hsiang Huang, Li Wei Kang*


研究成果: 雜誌貢獻期刊論文同行評審

102 引文 斯高帕斯(Scopus)


Images/videos captured from outdoor visual devices are usually degraded by turbid media, such as haze, smoke, fog, rain, and snow. Haze is the most common one in outdoor scenes due to the atmosphere conditions. In this paper, a novel deep learning-based architecture (denoted by MSRL-DehazeNet) for single image haze removal relying on multi-scale residual learning (MSRL) and image decomposition is proposed. Instead of learning an end-to-end mapping between each pair of hazy image and its corresponding haze-free one adopted by most existing learning-based approaches, we reformulate the problem as restoration of the image base component. Based on the decomposition of a hazy image into the base and the detail components, haze removal (or dehazing) can be achieved by both of our multi-scale deep residual learning and our simplified U-Net learning only for mapping between hazy and haze-free base components, while the detail component is further enhanced via the other learned convolutional neural network (CNN). Moreover, benefited by the basic building block of our deep residual CNN architecture and our simplified U-Net structure, the feature maps (produced by extracting structural and statistical features), and each previous layer can be fully preserved and fed into the next layer. Therefore, possible color distortion in the recovered image would be avoided. As a result, the final haze-removed (or dehazed) image is obtained by integrating the haze-removed base and the enhanced detail image components. Experimental results have demonstrated good effectiveness of the proposed framework, compared with state-of-the-art approaches.

頁(從 - 到)3153-3167
期刊IEEE Transactions on Image Processing
出版狀態已發佈 - 2020

ASJC Scopus subject areas

  • 軟體
  • 電腦繪圖與電腦輔助設計


深入研究「Multi-Scale Deep Residual Learning-Based Single Image Haze Removal via Image Decomposition」主題。共同形成了獨特的指紋。