Perceptual Extreme Super Resolution Network with Receptive Field Block

26 May 2020  ·  Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo ·

Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly. To tackle this difficulty, we develop a super resolution network with receptive field block based on Enhanced SRGAN. We call our network RFB-ESRGAN. The key contributions are listed as follows. First, for the purpose of extracting multi-scale information and enhance the feature discriminability, we applied receptive field block (RFB) to super resolution. RFB has achieved competitive results in object detection and classification. Second, instead of using large convolution kernels in multi-scale receptive field block, several small kernels are used in RFB, which makes us be able to extract detailed features and reduce the computation complexity. Third, we alternately use different upsampling methods in the upsampling stage to reduce the high computation complexity and still remain satisfactory performance. Fourth, we use the ensemble of 10 models of different iteration to improve the robustness of model and reduce the noise introduced by each individual model. Our experimental results show the superior performance of RFB-ESRGAN. According to the preliminary results of NTIRE 2020 Perceptual Extreme Super-Resolution Challenge, our solution ranks first among all the participants.

PDF Abstract


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution DIV8K test - 16x upscaling RFB-ESRGAN PSNR 23.38 # 1
LPIPS 0.348 # 1
Image Super-Resolution DIV8K val - 16x upscaling RFB-ESRGAN PSNR 24.03 # 2
LPIPS 0.345 # 2