Gated Multiple Feedback Network for Image Super-Resolution

9 Jul 2019  ·  Qilei Li, Zhen Li, Lu Lu, Gwanggil Jeon, Kai Liu, Xiaomin Yang ·

The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era. However, in most existing DL based image SR networks, the information flows are solely feedforward, and the high-level features cannot be fully explored. In this paper, we propose the gated multiple feedback network (GMFN) for accurate image SR, in which the representation of low-level features are efficiently enriched by rerouting multiple high-level features. We cascade multiple residual dense blocks (RDBs) and recurrently unfolds them across time. The multiple feedback connections between two adjacent time steps in the proposed GMFN exploits multiple high-level features captured under large receptive fields to refine the low-level features lacking enough contextual information. The elaborately designed gated feedback module (GFM) efficiently selects and further enhances useful information from multiple rerouted high-level features, and then refine the low-level features with the enhanced high-level information. Extensive experiments demonstrate the superiority of our proposed GMFN against state-of-the-art SR methods in terms of both quantitative metrics and visual quality. Code is available at https://github.com/liqilei/GMFN.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution BSD100 - 4x upscaling GMFN PSNR 27.74 # 17
SSIM 0.7421 # 20
Image Super-Resolution Manga109 - 4x upscaling GMFN PSNR 31.24 # 22
SSIM 0.9174 # 21
Image Super-Resolution Set14 - 4x upscaling GMFN PSNR 28.84 # 26
SSIM 0.7888 # 26
Image Super-Resolution Urban100 - 4x upscaling GMFN PSNR 26.69 # 19
SSIM 0.8048 # 17

Methods


No methods listed for this paper. Add relevant methods here