Real image super-resolution network for simplifying the degradation model
In the task of image super-resolution,bicubic down-sampling is commonly used to construct datasets for training net-works.However,due to the fixed degradation model,bicubic down-sampling results in low generalization ability of the network and cannot be used for real-world low-resolution images.To address this problem,this paper proposes a preprocessing module that com-bines with the network obtained from the bicubic down-sampling dataset to improve its generalization ability while reducing resource consumption.In addition,this paper also designs feature learning training strategies and multi-task joint training strategies for differ-ent accuracy requirements.By adopting corresponding training strategies according to different requirements,it can meet the accura-cy requirements while having the characteristics of low computational resource consumption,fast training speed,and wide applica-bility.Experiments have shown that adding a network with a preprocessing module can achieve greater improvements in reconstruc-tion effect and perceptual quality with less model parameter increase,and further improve accuracy through different strategies.