Fully Quantized image Super-Resolution networks

Hu Wang, Peng Chen, Bohan Zhuang, Chunhua Shen

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

11 Citations (Scopus)


With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, real-time and energy-efficient image Super-Resolution (SR) methods. A prevailing method for improving inference efficiency is model quantization, which allows for replacing the expensive floating-point operations with efficient bitwise arithmetic. To date, it is still challenging for quantized SR frameworks to deliver a 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 obtaining end-to-end quantized models for all layers, especially including skip connections, which was rarely addressed in the literature of SR quantization. We further identify obstacles faced by low-bit SR networks and propose a novel method to counteract them accordingly. The difficulties are caused by 1) for SR task, due to the existence of skip connections, high-resolution feature maps would occupy a huge amount of memory spaces; 2) activation and weight distributions being vastly distinctive in different layers; 3) 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 with low-bits quantization is able to achieve on par performance compared with the full-precision counterparts on five benchmark datasets and surpass the state-of-the-art quantized SR methods with significantly reduced computational cost and memory consumption. Code is available at https://git.io/JWxPp.

Original languageEnglish
Title of host publicationProceedings of the 29th ACM International Conference on Multimedia
EditorsLiqiang Nie, Qianru Sun, Peng Cui
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages9
ISBN (Electronic)9781450386517
Publication statusPublished - 2021
EventACM International Conference on Multimedia 2021 - Chengdu, China
Duration: 20 Oct 202124 Oct 2021
Conference number: 29th
https://dl.acm.org/doi/proceedings/10.1145/3474085 (Proceedings)
https://2021.acmmm.org/ (Website)


ConferenceACM International Conference on Multimedia 2021
Abbreviated titleMM 2021
Internet address


  • image super-resolution
  • network quantization

Cite this