Loughborough University
Browse
ESWA-D-22-08672_R2.pdf (2.07 MB)

Stereoscopic image super-resolution with interactive memory learning

Download (2.07 MB)
journal contribution
posted on 2023-06-12, 08:39 authored by Xiangyuan Zhu, Kehua Guo, Tian Qiu, Hui FangHui Fang, Zheng Wu, Xuyang Tan, Chao Liu
Stereo image super-resolution aims to exploit the complementary information between image pairs and generate images with high resolution and rich details. However, existing methods explicitly calculate the similarity between image patches or pixels to build correspondence between different views. These hard-matching methods leave deep semantic information between image pairs unexplored. In this paper, a stereo image super-resolution method with interactive memory learning is designed to take advantage of the complementary information of different views in an implicit way. Specifically, we propose an interactive memory learning strategy to implicitly capture the semantic similarity between different views and design a feature dual-aggregation module for feature refinement. Extensive experiments on different datasets achieve state-of-the-art results, demonstrating that our method effectively boosts the quantitative and qualitative results of stereoscopic image pairs. Code can be found at: https://github.com/zhuxiangyuan1/IMLnet.

Funding

Natural Science Foundation of China under Grant 62076255 and Grant 62105370

Open Research Projects of Zhejiang Lab, China (NO. 2022RC0AB07)

Hunan Provincial Science and Technology Plan, China Project 2020SK2059

Key projects of Hunan Education Department, China 20A88

National Science Foundation of Hunan Province, China 2021JJ30082

History

School

  • Science

Department

  • Computer Science

Published in

Expert Systems with Applications

Volume

227

Publisher

Elsevier

Version

  • AM (Accepted Manuscript)

Rights holder

© Elsevier

Publisher statement

This paper was accepted for publication in the journal Expert Systems with Applications and the definitive published version is available at https://doi.org/10.1016/j.eswa.2023.120143

Acceptance date

2023-04-11

Publication date

2023-05-05

Copyright date

2023

ISSN

0957-4174

eISSN

1873-6793

Language

  • en

Depositor

Dr Hui Fang. Deposit date: 9 June 2023

Article number

120143

Usage metrics

    Loughborough Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC