# Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices

arXiv: https://arxiv.org/abs/2105.10288 · HTML: https://mlsanity.com/paper/2105.10288/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 29 of 29)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [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)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy](https://mlsanity.com/paper/1711.05852/) (2017)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [Wide Activation for Efficient and Accurate Image Super-Resolution](https://mlsanity.com/paper/1808.08718/) (2018)
- [PAMS: Quantized Super-Resolution via Parameterized Max Scale](https://mlsanity.com/paper/2011.04212/) (2020)
- [AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2009.06943/) (2020)
- [Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07825/) (2021)
- [Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups](https://mlsanity.com/paper/1605.06489/) (2016)
- [A Quantization-Friendly Separable Convolution for MobileNets](https://mlsanity.com/paper/1803.08607/) (2018)
- [AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results](https://mlsanity.com/paper/1911.01249/) (2019)

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

- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05910/) (2022)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [edge-SR: Super-Resolution For The Masses](https://mlsanity.com/paper/2108.10335/) (2021)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution](https://mlsanity.com/paper/2208.11609/) (2022)
- [Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Network](https://mlsanity.com/paper/2305.02126/) (2023)
- [Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration](https://mlsanity.com/paper/2412.08939/) (2024)
- [Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks](https://mlsanity.com/paper/2307.13337/) (2023)
- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://mlsanity.com/paper/2303.04336/) (2023)
- [IMDeception: Grouped Information Distilling Super-Resolution Network](https://mlsanity.com/paper/2204.11463/) (2022)
- [XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation](https://mlsanity.com/paper/2208.14655/) (2022)
- [Real-Time Super-Resolution for Real-World Images on Mobile Devices](https://mlsanity.com/paper/2206.01777/) (2022)
- [Efficient neural supersampling on a novel gaming dataset](https://mlsanity.com/paper/2308.01483/) (2023)
- [Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices](https://mlsanity.com/paper/2206.00291/) (2022)
- [NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution](https://mlsanity.com/paper/2212.09501/) (2022)
- [ACNPU: A 4.75TOPS/W 1080P@30FPS Super Resolution Accelerator with Decoupled Asymmetric Convolution](https://mlsanity.com/paper/2308.15807/) (2023)
- [Task-driven single-image super-resolution reconstruction of document scans](https://mlsanity.com/paper/2407.08993/) (2024)
- [Decoder-Free Distillation for Quantized Image Restoration](https://mlsanity.com/paper/2603.09624/) (2026)
- [Machine Learning Advances aiding Recognition and Classification of Indian Monuments and Landmarks](https://mlsanity.com/paper/2107.14070/) (2021)
- [Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images](https://mlsanity.com/paper/2308.11365/) (2023)
- [TMSR: Tiny Multi-path CNNs for Super Resolution](https://mlsanity.com/paper/2312.01644/) (2023)
- [Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Content](https://mlsanity.com/paper/2501.01773/) (2025)
- [Crafting Query-Aware Selective Attention for Single Image Super-Resolution](https://mlsanity.com/paper/2504.06634/) (2025)
- [Task-driven real-world super-resolution of document scans](https://mlsanity.com/paper/2506.06953/) (2025)
- [Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content](https://mlsanity.com/paper/2602.11339/) (2026)

## Abstract (arXiv)

Single-Image Super Resolution (SISR) is a classical computer vision problem and it has been studied for over decades. With the recent success of deep learning methods, recent work on SISR focuses solutions with deep learning methodologies and achieves state-of-the-art results. However most of the state-of-the-art SISR methods contain millions of parameters and layers, which limits their practical applications. In this paper, we propose a hardware (Synaptics Dolphin NPU) limitation aware, extremely lightweight quantization robust real-time super resolution network (XLSR). The proposed model's building block is inspired from root modules for Image classification. We successfully applied root modules to SISR problem, further more to make the model uint8 quantization robust we used Clipped ReLU at the last layer of the network and achieved great balance between reconstruction quality and runtime. Furthermore, although the proposed network contains 30x fewer parameters than VDSR its performance surpasses it on Div2K validation set. The network proved itself by winning Mobile AI 2021 Real-Time Single Image Super Resolution Challenge.