# EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution

arXiv: https://arxiv.org/abs/2605.17470 · HTML: https://mlsanity.com/paper/2605.17470/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [MixConv: Mixed Depthwise Convolutional Kernels](https://mlsanity.com/paper/1907.09595/) (2019)
- [InceptionNeXt: When Inception Meets ConvNeXt](https://mlsanity.com/paper/2303.16900/) (2023)
- [UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition](https://mlsanity.com/paper/2311.15599/) (2023)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [MogaNet: Multi-order Gated Aggregation Network](https://mlsanity.com/paper/2211.03295/) (2022)
- [Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution](https://mlsanity.com/paper/2302.13800/) (2023)
- [N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.11436/) (2022)
- [ShuffleMixer: An Efficient ConvNet for Image Super-Resolution](https://mlsanity.com/paper/2205.15175/) (2022)
- [MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration](https://mlsanity.com/paper/2412.20066/) (2024)
- [HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution](https://mlsanity.com/paper/2407.05878/) (2024)
- [Multi-scale Attention Network for Single Image Super-Resolution](https://mlsanity.com/paper/2209.14145/) (2022)
- [See More Details: Efficient Image Super-Resolution by Experts Mining](https://mlsanity.com/paper/2402.03412/) (2024)

## Built on by (most cited first, 1 of 1)

- [DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation](https://mlsanity.com/paper/2608.09536/) (2026)

## Abstract (arXiv)

Image super-resolution (SR) aims to reconstruct high-quality, high-resolution (HR) images from low-resolution (LR) inputs and plays a critical role in various downstream applications. Despite recent advancements, balancing reconstruction fidelity and computational efficiency remains a fundamental challenge, particularly in resource-constrained scenarios. While existing lightweight methods attempt to expand receptive fields, many of them either incur substantial computational overhead, naively scale up kernel sizes, or lack mechanisms for coherent multi-scale integration, limiting their overall effectiveness and scalability. To address these limitations, we propose EchoSR, an efficient context-harnessing framework for lightweight image super-resolution, which unifies multi-scale receptive field modeling and hierarchical context fusion. EchoSR decouples feature learning into disentangled local, multi-scale, and global modeling stages through an efficient context-harnessing strategy, and further promotes seamless cross-scale integration via a cross-scale overlapping fusion mechanism. Extensive experiments have shown that EchoSR consistently outperforms state-of-the-art lightweight super-resolution methods across multiple benchmarks, while also achieving a faster speed (~ 2×). The source code is available at https://github.com/funnyWang-Echoes/EchoSR.