# Omni Aggregation Networks for Lightweight Image Super-Resolution

arXiv: https://arxiv.org/abs/2304.10244 · HTML: https://mlsanity.com/paper/2304.10244/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 72 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)

## Built on by (most cited first, 30 of 62)

- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing](https://mlsanity.com/paper/2408.14180/) (2024)
- [HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution](https://mlsanity.com/paper/2407.05878/) (2024)
- [RealViformer: Investigating Attention for Real-World Video Super-Resolution](https://mlsanity.com/paper/2407.13987/) (2024)
- [The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2504.10686/) (2025)
- [Progressive Focused Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2503.20337/) (2025)
- [The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2604.03198/) (2026)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [See More Details: Efficient Image Super-Resolution by Experts Mining](https://mlsanity.com/paper/2402.03412/) (2024)
- [CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.06896/) (2025)
- [Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach](https://mlsanity.com/paper/2401.05633/) (2024)
- [Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration](https://mlsanity.com/paper/2309.06023/) (2023)
- [PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution](https://mlsanity.com/paper/2504.07758/) (2025)
- [OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution](https://mlsanity.com/paper/2308.08114/) (2023)
- [Boosting Flow-based Generative Super-Resolution Models via Learned Prior](https://mlsanity.com/paper/2403.10988/) (2024)
- [Partial Large Kernel CNNs for Efficient Super-Resolution](https://mlsanity.com/paper/2404.11848/) (2024)
- [Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks](https://mlsanity.com/paper/2503.04223/) (2025)
- [C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales](https://mlsanity.com/paper/2503.13740/) (2025)
- [Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation](https://mlsanity.com/paper/2604.11564/) (2026)
- [Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution](https://mlsanity.com/paper/2407.16232/) (2024)
- [MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution](https://mlsanity.com/paper/2411.17214/) (2024)
- [Emulating Self-attention with Convolution for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.06671/) (2025)
- [Blind Video Super-Resolution based on Implicit Kernels](https://mlsanity.com/paper/2503.07856/) (2025)
- [PromptSR: Cascade Prompting for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2507.04118/) (2025)
- [FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.10043/) (2025)
- [Enhanced Generative Structure Prior for Chinese Text Image Super-resolution](https://mlsanity.com/paper/2508.07537/) (2025)
- [ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration](https://mlsanity.com/paper/2603.02581/) (2026)
- [Cross-Spatial Pixel Integration and Cross-Stage Feature Fusion Based Transformer Network for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2307.02974/) (2023)
- [SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution](https://mlsanity.com/paper/2406.09168/) (2024)

## Abstract (arXiv)

While lightweight ViT framework has made tremendous progress in image super-resolution, its uni-dimensional self-attention modeling, as well as homogeneous aggregation scheme, limit its effective receptive field (ERF) to include more comprehensive interactions from both spatial and channel dimensions. To tackle these drawbacks, this work proposes two enhanced components under a new Omni-SR architecture. First, an Omni Self-Attention (OSA) block is proposed based on dense interaction principle, which can simultaneously model pixel-interaction from both spatial and channel dimensions, mining the potential correlations across omni-axis (i.e., spatial and channel). Coupling with mainstream window partitioning strategies, OSA can achieve superior performance with compelling computational budgets. Second, a multi-scale interaction scheme is proposed to mitigate sub-optimal ERF (i.e., premature saturation) in shallow models, which facilitates local propagation and meso-/global-scale interactions, rendering an omni-scale aggregation building block. Extensive experiments demonstrate that Omni-SR achieves record-high performance on lightweight super-resolution benchmarks (e.g., 26.95 dB@Urban100 × 4 with only 792K parameters). Our code is available at urlhttps://github.com/Francis0625/Omni-SR.