Learning-based methods have attracted considerable interest in image dehazing. However, most existing methods are not well adapted to different hazy conditions, especially when dealing with the heavily hazy scene. There is often a significant amount of haze that remains in the images recovered by most methods. To address this issue, we propose an end-to-end Haze Concentration Adaptive Network (HCAN), including a pyramid feature extractor (PFE), a feature enhancement module (FEM), and a multi-scale feature attention module (MSFAM) for image dehazing. Specifically, PFE based on the feature pyramid structure leverages complementary features from different CNN layers to help the clear image prediction. Then, FEM fuses four kinds of images with different haze density (i.e., three recovered images in the FEM with light haze density, and the input hazy image with strong haze condition) to guide the network to adaptively perceive images under different haze conditions. Finally, MSFAM is designed under two principles, multi-scale structure and attention mechanism. It is used to help the network produce a clear image with more details, and ease the network training. Comprehensive experiments demonstrate that the proposed HCAN performs favorably against the state-of-the-art methods in terms of PSNR, SSIM, and visual effect. The results, per-trained models and code are available at https://github.com/TaoWangzj/HCAN.

基于学习的方法在图像去雾方面引起了极大的兴趣。但是，大多数现有方法不能很好地适应不同的朦胧条件，尤其是在处理重度朦胧的场景时。大多数方法恢复的图像中通常会残留大量的雾度。为了解决这个问题，我们提出了一个端到端的雾度集中自适应网络（HCAN），包括金字塔特征提取器（PFE），特征增强模块（FEM）和多尺度特征关注模块（MSFAM），用于图像除雾。具体来说，基于特征金字塔结构的PFE利用来自不同CNN层的互补特征来帮助进行清晰的图像预测。然后，FEM融合了四种具有不同雾度密度的图像（即，FEM中具有三度雾度密度的三个恢复图像，以及具有强雾度条件的输入雾度图像），以指导网络在不同雾度条件下自适应地感知图像。最后，MSFAM是根据两个原则设计的，即多尺度结构和注意机制。它用于帮助网络生成具有更多细节的清晰图像，并简化网络培训。全面的实验表明，所提出的HCAN在PSNR，SSIM和视觉效果方面均优于最新技术。结果，经过训练的模型和代码可在https://github.com/TaoWangzj/HCAN获得。它用于帮助网络生成具有更多细节的清晰图像，并简化网络培训。全面的实验表明，所提出的HCAN在PSNR，SSIM和视觉效果方面均优于最新技术。结果，经过训练的模型和代码可在https://github.com/TaoWangzj/HCAN获得。它用于帮助网络生成具有更多细节的清晰图像，并简化网络培训。全面的实验表明，所提出的HCAN在PSNR，SSIM和视觉效果方面均优于最新技术。结果，经过训练的模型和代码可在https://github.com/TaoWangzj/HCAN获得。