Deeply-Recursive Convolutional Network for Image Super-Resolution

2015/11/14 by Jiwon Kim, Kim, Jiwon, Jung Kwon Lee +3 · 25 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1511.04491

CVPR 2016 Oral

openalex publication_date 2015/11/14 · arxiv created 2016/11/11 · arxiv updated 2016/11/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive-supervision and skip-connection. Our method outperforms previous methods by a large margin.

Citations

• Gradient-based learning applied to document recognition
• Deeply-Supervised Nets
• Fully Convolutional Networks for Semantic Segmentation
• MatConvNet - Convolutional Neural Networks for MATLAB

Cited by

• HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention
• Dual-domain Adaptation Networks for Realistic Image Super-resolution
• MRI Super-Resolution with Deep Learning: A Comprehensive Survey
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results
• Ultra-High-Definition Reference-Based Landmark Image Super-Resolution with Generative Diffusion Prior
• Fourier-Guided Attention Upsampling for Image Super-Resolution
• Blind Super Resolution with Reference Images and Implicit Degradation Representation
• A Systematic Investigation on Deep Learning-Based Omnidirectional Image and Video Super-Resolution
• Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolution
• Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems
• Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations
• Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
• Efficient Star Distillation Attention Network for Lightweight Image Super-Resolution
• Application of convolutional neural networks in image super-resolution
• A Tree-guided CNN for image super-resolution
• Content-adaptive Representation Learning for Fast Image Super-resolution
• Learning to Extract a Video Sequence from a Single Motion-Blurred Image
• Towards Lightweight Hyperspectral Image Super-Resolution with Depthwise Separable Dilated Convolutional Network
• Augmenting Perceptual Super-Resolution via Image Quality Predictors
• RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
• Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution
• TTRD3: Texture Transfer Residual Denoising Dual Diffusion Model for Remote Sensing Image Super-Resolution
• Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution
• Improving World Models using Deep Supervision with Linear Probes

Related

• Accurate Image Super-Resolution Using Very Deep Convolutional Networks
• Image Super-Resolution Using Deep Convolutional Networks
• Image Super-Resolution Using Deep Convolutional Networks
• A Deep Journey into Super-resolution: A survey
• Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network