Multi-scale interaction network for stereo image super-resolution
It addresses the problem of improving stereo image super-resolution for computer vision applications by better exploiting intra-view and cross-view information.
This paper proposes a multi-scale interaction network for stereo image super-resolution, achieving competitive results that outperform most state-of-the-art methods.
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.