Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network

30 Nov 2018  ·  Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee ·

Recently, several deep learning-based image super-resolution methods have been developed by stacking massive numbers of layers. However, this leads too large model sizes and high computational complexities, thus some recursive parameter-sharing methods have been also proposed... Nevertheless, their designs do not properly utilize the potential of the recursive operation. In this paper, we propose a novel, lightweight, and efficient super-resolution method to maximize the usefulness of the recursive architecture, by introducing block state-based recursive network. By taking advantage of utilizing the block state, the recursive part of our model can easily track the status of the current image features. We show the benefits of the proposed method in terms of model size, speed, and efficiency. In addition, we show that our method outperforms the other state-of-the-art methods. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution BSD100 - 4x upscaling BSRN PSNR 27.57 # 21
SSIM 0.7353 # 24
Image Super-Resolution Set14 - 4x upscaling BSRN PSNR 28.56 # 22
SSIM 0.7803 # 27
Image Super-Resolution Set5 - 4x upscaling BSRN PSNR 32.14 # 21
SSIM 0.8937 # 26
Image Super-Resolution Urban100 - 4x upscaling BSRN PSNR 26.03 # 22
SSIM 0.7835 # 21


No methods listed for this paper. Add relevant methods here