File(s) under embargo
Reason: Publisher requirement.
until file(s) become available
Stereoscopic image super-resolution with interactive memory learning
journal contributionposted 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.
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
- Computer Science
Published inExpert Systems with Applications
- AM (Accepted Manuscript)
Rights holder© Elsevier
Publisher statementThis 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