# Fully Quantized Image Super-Resolution Networks

arXiv: https://arxiv.org/abs/2011.14265 · HTML: https://mlsanity.com/paper/2011.14265/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2020.

## Built on by (most cited first, 19 of 19)

- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks](https://mlsanity.com/paper/2203.03844/) (2022)
- [Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05910/) (2022)
- [Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach](https://mlsanity.com/paper/2204.09992/) (2022)
- [Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2308.05022/) (2023)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [Reciprocal Attention Mixing Transformer for Lightweight Image Restoration](https://mlsanity.com/paper/2305.11474/) (2023)
- [Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks](https://mlsanity.com/paper/2307.13337/) (2023)
- [Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues](https://mlsanity.com/paper/2409.14330/) (2024)
- [Outlier-Aware Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2511.00682/) (2025)
- [E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow](https://mlsanity.com/paper/2207.06893/) (2022)
- [Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training](https://mlsanity.com/paper/2304.01805/) (2023)
- [Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks](https://mlsanity.com/paper/2305.05888/) (2023)
- [Decoder-Free Distillation for Quantized Image Restoration](https://mlsanity.com/paper/2603.09624/) (2026)
- [Kernel Adversarial Learning for Real-world Image Super-resolution](https://mlsanity.com/paper/2104.09008/) (2021)
- [Fully Quantized Always-on Face Detector Considering Mobile Image Sensors](https://mlsanity.com/paper/2311.01001/) (2023)
- [Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design](https://mlsanity.com/paper/2407.02813/) (2024)
- [Any Orthogonal Transform Will Do: Range Reduction Explains Rotation-Based Quantization for Super-Resolution](https://mlsanity.com/paper/2601.21069/) (2026)
- [QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks](https://mlsanity.com/paper/2605.22351/) (2026)

## Abstract (arXiv)

With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods. A prevailing method for improving the inference efficiency is model quantization, which allows for replacing the expensive floating-point operations with efficient fixed-point or bitwise arithmetic. To date, it is still challenging for quantized SR frameworks to deliver feasible accuracy-efficiency trade-off. Here, we propose a Fully Quantized image Super-Resolution framework (FQSR) to jointly optimize efficiency and accuracy. In particular, we target on obtaining end-to-end quantized models for all layers, especially including skip connections, which was rarely addressed in the literature. We further identify training obstacles faced by low-bit SR networks and propose two novel methods accordingly. The two difficulites are caused by 1) activation and weight distributions being vastly distinctive in different layers; 2) the inaccurate approximation of the quantization. We apply our quantization scheme on multiple mainstream super-resolution architectures, including SRResNet, SRGAN and EDSR. Experimental results show that our FQSR using low bits quantization can achieve on par performance compared with the full-precision counterparts on five benchmark datasets and surpass state-of-the-art quantized SR methods with significantly reduced computational cost and memory consumption.