激光与光电子学进展, 2020, 57 (6): 061015, 网络出版: 2020-03-06   

基于多尺度融合和对抗训练的图像去雾算法 下载: 1403次

Image Dehazing Algorithm Based on Multi-Scale Fusion and Adversarial Training
作者单位
天津大学电气自动化与信息工程学院, 天津 300072
摘要
针对传统去雾算法结果中颜色和对比度失真等问题,提出了一种基于多尺度融合和对抗训练的图像去雾算法。采用多尺度特征提取模块从多个不同尺度中提取雾霾相关特征,利用残差密集连接模块实现图像特征的交互,避免了梯度消失。由于其不基于大气散射模型,直接将图像的浅层特征和深层特征进行多尺度融合,所以克服了物理模型的不精确性。去雾网络的训练采用生成对抗机制,由多尺度特征提取模块和残差密集连接模块构成的生成器估计清晰的无雾图像,由两个不同尺度感受野的子网络构成的鉴别器完成对抗训练。在RESIDE(Realistic single image dehazing)数据集上进行对比实验,结果表明本算法生成的去雾图像在全参考和无参考的视觉质量指标方面优于其他对比算法。
Abstract
Aim

ing at solving the problems of color and contrast distortions in traditional dehazing algorithms, we propose an image dehazing algorithm based on multi-scale fusion and adversarial training. The multi-scale feature extraction block is used to extract haze-relevant features from different scales, and the residual-and-densely-connected block is used to realize the interaction of image features and avoid gradient vanishing. Because the algorithm is not based on the atmospheric scattering model and directly fuses the shallow and deep features of the image in the multi-scale manner, so it overcomes the inaccuracy of physical model. The dehazing network is trained via the generative adversarial mechanism, the generator uses the multi-scale feature extraction block and the residual-and-densely-connected block to estimate the haze-free image, and the discriminator consisting of two sub-networks with different receptive fields carries out the adversarial training. Comparison experiments on the RESIDE (Realistic single image dehazing) dataset show that the dehazed images generated by the proposed algorithm are more visually pleasant than those by other algorithms in terms of full-reference and no-reference visual quality indicators.

刘宇航, 吴帅. 基于多尺度融合和对抗训练的图像去雾算法[J]. 激光与光电子学进展, 2020, 57(6): 061015. Yuhang Liu, Shuai Wu. Image Dehazing Algorithm Based on Multi-Scale Fusion and Adversarial Training[J]. Laser & Optoelectronics Progress, 2020, 57(6): 061015.

本文已被 4 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!