DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors

Abstract

Recently, single-image super-resolution has made great progress owing to the development of deep convolutional neural networks (CNNs). The vast majority of CNN-based models use a pre-defined upsampling operator, such as bicubic interpolation, to upscale input low-resolution images to the desired size and learn non-linear mapping between the interpolated image and ground truth high-resolution (HR) image. However, interpolation processing can lead to visual artifacts as details are over-smoothed, particularly when the super-resolution factor is high. In this paper, we propose a Deep Recurrent Fusion Network (DRFN), which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images. We adopt a deep recurrence learning strategy and thus have a larger receptive field, which is conducive to reconstructing an image more accurately. Furthermore, we show that the multi-level fusion structure is suitable for dealing with image super-resolution problems. Extensive benchmark evaluations demonstrate that the proposed DRFN performs better than most current deep learning methods in terms of accuracy and visual effects, especially for large-scale images, while using fewer parameters.

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution
• Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning
• Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

Cited by in corpus (14)

• A Two-Stage Attentive Network for Single Image Super-Resolution
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Progressive Glass Segmentation
• Iterative Network for Image Super-Resolution
• Camouflaged Object Segmentation with Distraction Mining
• Smart Scribbles for Image Mating
• Large-Field Contextual Feature Learning for Glass Detection
• Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
• Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolution
• Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention
• Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking
• Asymmetric CNN for image super-resolution
• Learning regularization and intensity-gradient-based fidelity for single image super resolution
• Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking