Nonlocal Similarity Modeling and Deep CNN Gradient Prior for Super Resolution

作者：Ren, Chao^*; He, Xiaohai; Pu, Yifei

来源：IEEE Signal Processing Letters, 2018, 25(7): 916-920.

DOI：10.1109/LSP.2018.2829766

• Gradient prior (GP)
• group similarity reliability (GSR)
• nonlocal similarity
• super resolution

This letter presents a novel super-resolution (SR) method via nonlocal similarity modeling and deep convolutional neural network (CNN) gradient prior (GP). Specifically, on the one hand, the group similarity reliability (GSR) strategy is proposed for improving the adaptive high-dimensional nonlocal total variation (AHNLTV) model [statistical prior, GSR-based AHNLTV (GA)], which captures the structures of the underlying high-resolution (HR) image via the image itself. On the other hand, the GP is learned by using the deep CNN (learned prior), which predicts the gradients from external images. Finally, the GA-GP approach is proposed by incorporating the two complementary priors. The results show that GA-GP achieves better performance than other state-of-the-art SR methods.

• 出版日期2018-7
• 单位四川大学