基于深度特征学习的图像超分辨率重建

Image Super-resolution Based on Deep Learning Features

基于学习的图像超分辨率(Super-resolution,SR)算法利用样本先验知识来重建图像,相较于其他重建方法拥有明显的优势,也是近年来研究的热点.论文首先分析了影响图像重建质量的因素,然后对基于卷积神经网络的图像超分辨率重建算法(Super-resolution convolutional neural network,SRCNN)提出了两点改进:我们用随机线性纠正单元(Randomized rectified linear unit,RRe LU)去避免原有网络学习中对图像某些重要的信息过压缩,同时我们用NAG(Nesterov s accelerated gradient)方法去加速网络的收敛并且避免了网络在梯度更新的时候产生较大的震荡.最后通过实验验证了我们改进网络可以获得更好的主观视觉评价和客观量化评价.

Learning-based image super-resolution method is a research hotspot in recent years which uses prior knowledge of sample to reconstruct the image and has obvious advantages over other reconstruction methods. In this paper, we first analyze the factors of reconstructed image quality. Then we use randomized rectified linear unit （RReLU） to solve the problem of over compression in the original network. Besides, Nesterov＇s accelerated gradient （NAG） is invoked to accelerate convergence and avoid large oscillations. Finally, we conduct a quantitative experiments to prove the validity of the proposed algorithm.