Multi-scale interaction network for stereo image super-resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Liyi, Qi, Lin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914585541345280
author Xu, Liyi
Qi, Lin
author_facet Xu, Liyi
Qi, Lin
contents Stereo image super-resolution aims to generate high-resolution images by leveraging complementary information from binocular systems. Although previous studies have achieved impressive results, the potential of intra-view and cross-view information has not been fully exploited. To address this issue, we propose a novel multi-scale interaction network for stereo image super-resolution. Specifically, we design a Multi-scale Spatial-Channel Attention Module that utilizes multi-scale large separable kernel attention and simple channel attention to improve intra-view feature extraction. Additionally, we propose a Dual-View Epipolar Attention Module, utilizing an optimal transport algorithm to achieve more accurate matching along the epipolar line. Extensive experimental and ablation studies show that our method achieves competitive results that outperform most SOTA methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21913
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-scale interaction network for stereo image super-resolution
Xu, Liyi
Qi, Lin
Computer Vision and Pattern Recognition
Stereo image super-resolution aims to generate high-resolution images by leveraging complementary information from binocular systems. Although previous studies have achieved impressive results, the potential of intra-view and cross-view information has not been fully exploited. To address this issue, we propose a novel multi-scale interaction network for stereo image super-resolution. Specifically, we design a Multi-scale Spatial-Channel Attention Module that utilizes multi-scale large separable kernel attention and simple channel attention to improve intra-view feature extraction. Additionally, we propose a Dual-View Epipolar Attention Module, utilizing an optimal transport algorithm to achieve more accurate matching along the epipolar line. Extensive experimental and ablation studies show that our method achieves competitive results that outperform most SOTA methods.
title Multi-scale interaction network for stereo image super-resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.21913