Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-scale interaction network for stereo image super-resolution

About

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.

Liyi Xu, Lin Qi• 2026

Related benchmarks

TaskDatasetResultRank
Stereo Image Super-ResolutionKITTI 2012 (test)
PSNR27.07
66
Stereo Image Super-ResolutionFlickr1024
PSNR24.03
30
Stereo Image Super-ResolutionKITTI 2015 (test)
PSNR26.88
17
Stereo Image Super-ResolutionMiddlebury (test)
PSNR29.98
8
Showing 4 of 4 rows

Other info

Follow for update