# Multi-Attention Based Ultra Lightweight Image Super-Resolution

arXiv: https://arxiv.org/abs/2008.12912 · HTML: https://mlsanity.com/paper/2008.12912/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [Residual Local Feature Network for Efficient Super-Resolution](https://mlsanity.com/paper/2205.07514/) (2022)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2112.08655/) (2021)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2207.02796/) (2022)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results](https://mlsanity.com/paper/2205.12633/) (2022)
- [Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers](https://mlsanity.com/paper/2305.17313/) (2023)
- [From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2211.16776/) (2022)
- [CompenHR: Efficient Full Compensation for High-resolution Projector](https://mlsanity.com/paper/2311.13409/) (2023)
- [LIPT: Latency-aware Image Processing Transformer](https://mlsanity.com/paper/2404.06075/) (2024)
- [MaxSR: Image Super-Resolution Using Improved MaxViT](https://mlsanity.com/paper/2307.07240/) (2023)
- [Semantic-Guided Global-Local Collaborative Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.16056/) (2025)
- [A High-Frequency Focused Network for Lightweight Single Image Super-Resolution](https://mlsanity.com/paper/2303.11701/) (2023)
- [EPNet: An Efficient Pyramid Network for Enhanced Single-Image Super-Resolution with Reduced Computational Requirements](https://mlsanity.com/paper/2312.13396/) (2023)
- [Lightweight single-image super-resolution network based on dual paths](https://mlsanity.com/paper/2409.06590/) (2024)
- [CubeFormer: A Simple yet Effective Baseline for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2412.02234/) (2024)
- [Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.14779/) (2025)
- [DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution](https://mlsanity.com/paper/2505.21262/) (2025)

## Abstract (arXiv)

Lightweight image super-resolution (SR) networks have the utmost significance for real-world applications. There are several deep learning based SR methods with remarkable performance, but their memory and computational cost are hindrances in practical usage. To tackle this problem, we propose a Multi-Attentive Feature Fusion Super-Resolution Network (MAFFSRN). MAFFSRN consists of proposed feature fusion groups (FFGs) that serve as a feature extraction block. Each FFG contains a stack of proposed multi-attention blocks (MAB) that are combined in a novel feature fusion structure. Further, the MAB with a cost-efficient attention mechanism (CEA) helps us to refine and extract the features using multiple attention mechanisms. The comprehensive experiments show the superiority of our model over the existing state-of-the-art. We participated in AIM 2020 efficient SR challenge with our MAFFSRN model and won 1st, 3rd, and 4th places in memory usage, floating-point operations (FLOPs) and number of parameters, respectively.