RefQSR: Reference-based Quantization for Image Super-Resolution Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Hongjae, Yoo, Jun-Sang, Jung, Seung-Won
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929300123418624
author Lee, Hongjae
Yoo, Jun-Sang
Jung, Seung-Won
author_facet Lee, Hongjae
Yoo, Jun-Sang
Jung, Seung-Won
contents Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting their use in resource-constrained environments. As a promising solution for computationally efficient network design, network quantization has been extensively studied. However, existing quantization methods developed for SISR have yet to effectively exploit image self-similarity, which is a new direction for exploration in this study. We introduce a novel method called reference-based quantization for image super-resolution (RefQSR) that applies high-bit quantization to several representative patches and uses them as references for low-bit quantization of the rest of the patches in an image. To this end, we design dedicated patch clustering and reference-based quantization modules and integrate them into existing SISR network quantization methods. The experimental results demonstrate the effectiveness of RefQSR on various SISR networks and quantization methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01690
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RefQSR: Reference-based Quantization for Image Super-Resolution Networks
Lee, Hongjae
Yoo, Jun-Sang
Jung, Seung-Won
Computer Vision and Pattern Recognition
Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance at the expense of increased computational costs, limiting their use in resource-constrained environments. As a promising solution for computationally efficient network design, network quantization has been extensively studied. However, existing quantization methods developed for SISR have yet to effectively exploit image self-similarity, which is a new direction for exploration in this study. We introduce a novel method called reference-based quantization for image super-resolution (RefQSR) that applies high-bit quantization to several representative patches and uses them as references for low-bit quantization of the rest of the patches in an image. To this end, we design dedicated patch clustering and reference-based quantization modules and integrate them into existing SISR network quantization methods. The experimental results demonstrate the effectiveness of RefQSR on various SISR networks and quantization methods.
title RefQSR: Reference-based Quantization for Image Super-Resolution Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.01690