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

arXiv: https://arxiv.org/abs/1908.08837 · HTML: https://mlsanity.com/paper/1908.08837/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2019.

## Built on by (most cited first, 24 of 24)

- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Towards Compact Single Image Super-Resolution via Contrastive Self-distillation](https://mlsanity.com/paper/2105.11683/) (2021)
- [A Two-Stage Attentive Network for Single Image Super-Resolution](https://mlsanity.com/paper/2104.10488/) (2021)
- [A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2112.04488/) (2021)
- [Learning for Unconstrained Space-Time Video Super-Resolution](https://mlsanity.com/paper/2102.13011/) (2021)
- [Asymmetric CNN for image super-resolution](https://mlsanity.com/paper/2103.13634/) (2021)
- [Smart Scribbles for Image Mating](https://mlsanity.com/paper/2103.17062/) (2021)
- [A heterogeneous group CNN for image super-resolution](https://mlsanity.com/paper/2209.12406/) (2022)
- [Progressive Glass Segmentation](https://mlsanity.com/paper/2209.02280/) (2022)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (2022)
- [T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing](https://mlsanity.com/paper/2106.02809/) (2021)
- [Large-Field Contextual Feature Learning for Glass Detection](https://mlsanity.com/paper/2209.04639/) (2022)
- [Image Super-resolution with An Enhanced Group Convolutional Neural Network](https://mlsanity.com/paper/2205.14548/) (2022)
- [Prior-Induced Information Alignment for Image Matting](https://mlsanity.com/paper/2106.14439/) (2021)
- [Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking](https://mlsanity.com/paper/2108.04521/) (2021)
- [Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution](https://mlsanity.com/paper/2403.16643/) (2024)
- [Cross-View Hierarchy Network for Stereo Image Super-Resolution](https://mlsanity.com/paper/2304.06236/) (2023)
- [Image super-resolution via dynamic network](https://mlsanity.com/paper/2310.10413/) (2023)
- [An Advanced Features Extraction Module for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04595/) (2024)
- [Kernelized Back-Projection Networks for Blind Super Resolution](https://mlsanity.com/paper/2302.08478/) (2023)
- [Learned Image Compression and Restoration for Digital Pathology](https://mlsanity.com/paper/2503.23862/) (2025)
- [Lightweight Improved Residual Network for Efficient Inverse Tone Mapping](https://mlsanity.com/paper/2307.03998/) (2023)
- [Fourier-Guided Attention Upsampling for Image Super-Resolution](https://mlsanity.com/paper/2508.10616/) (2025)
- [OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition](https://mlsanity.com/paper/2511.08133/) (2025)

## Abstract (arXiv)

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.