# Image Super-Resolution via Dual-State Recurrent Networks

arXiv: https://arxiv.org/abs/1805.02704 · HTML: https://mlsanity.com/paper/1805.02704/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2018.

## Built on by (most cited first, 22 of 22)

- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [COMISR: Compression-Informed Video Super-Resolution](https://mlsanity.com/paper/2105.01237/) (2021)
- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising](https://mlsanity.com/paper/2508.19649/) (2025)
- [Real-World Super-Resolution of Face-Images from Surveillance Cameras](https://mlsanity.com/paper/2102.03113/) (2021)
- [Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation](https://mlsanity.com/paper/2305.11317/) (2023)
- [Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond](https://mlsanity.com/paper/2203.05709/) (2022)
- [Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors](https://mlsanity.com/paper/2210.06002/) (2022)
- [Feedback Refined Local-Global Network for Super-Resolution of Hyperspectral Imagery](https://mlsanity.com/paper/2103.04354/) (2021)
- [SelFSR: Self-Conditioned Face Super-Resolution in the Wild via Flow Field Degradation Network](https://mlsanity.com/paper/2112.10683/) (2021)
- [A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning](https://mlsanity.com/paper/2302.11184/) (2023)
- [MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature](https://mlsanity.com/paper/2409.19835/) (2024)
- [Learned Image Compression and Restoration for Digital Pathology](https://mlsanity.com/paper/2503.23862/) (2025)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery](https://mlsanity.com/paper/2102.06102/) (2021)
- [Deep Fusion Prior for Plenoptic Super-Resolution All-in-Focus Imaging](https://mlsanity.com/paper/2110.05706/) (2021)
- [AffectSRNet : Facial Emotion-Aware Super-Resolution Network](https://mlsanity.com/paper/2502.09932/) (2025)

## Abstract (arXiv)

Advances in image super-resolution (SR) have recently benefited significantly from rapid developments in deep neural networks. Inspired by these recent discoveries, we note that many state-of-the-art deep SR architectures can be reformulated as a single-state recurrent neural network (RNN) with finite unfoldings. In this paper, we explore new structures for SR based on this compact RNN view, leading us to a dual-state design, the Dual-State Recurrent Network (DSRN). Compared to its single state counterparts that operate at a fixed spatial resolution, DSRN exploits both low-resolution (LR) and high-resolution (HR) signals jointly. Recurrent signals are exchanged between these states in both directions (both LR to HR and HR to LR) via delayed feedback. Extensive quantitative and qualitative evaluations on benchmark datasets and on a recent challenge demonstrate that the proposed DSRN performs favorably against state-of-the-art algorithms in terms of both memory consumption and predictive accuracy.