Feedback Network for Image Super-Resolution

Abstract

Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in an RNN with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at https://github.com/Paper99/SRFBN_CVPR19.

Accepted to CVPR 2019

References in corpus (5)

• Sketch-based Manga Retrieval using Manga109 Dataset
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Residual Dense Network for Image Super-Resolution
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• Top-Down Feedback for Crowd Counting Convolutional Neural Network

Cited by in corpus (6)

• Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution
• Feedback Graph Attention Convolutional Network for Medical Image Enhancement
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration
• Interpretable Deep Multimodal Image Super-Resolution
• Single Image Super-Resolution
• RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network