Multi-Level Feature Fusion Network for Lightweight Stereo Image Super-Resolution

TL;DR

This paper introduces MFFSSR, a lightweight stereo image super-resolution network that efficiently extracts and fuses multi-level features using hybrid attention and cross-view modules, achieving high-quality results with fewer parameters.

Contribution

The paper proposes a novel multi-level feature fusion network with hybrid attention and cross-view modules for efficient stereo image super-resolution.

Findings

Achieves superior super-resolution performance with fewer parameters.

Effectively extracts and fuses multi-level intra-view features.

Demonstrates improved detail and texture reconstruction.

Abstract

Stereo image super-resolution utilizes the cross-view complementary information brought by the disparity effect of left and right perspective images to reconstruct higher-quality images. Cascading feature extraction modules and cross-view feature interaction modules to make use of the information from stereo images is the focus of numerous methods. However, this adds a great deal of network parameters and structural redundancy. To facilitate the application of stereo image super-resolution in downstream tasks, we propose an efficient Multi-Level Feature Fusion Network for Lightweight Stereo Image Super-Resolution (MFFSSR). Specifically, MFFSSR utilizes the Hybrid Attention Feature Extraction Block (HAFEB) to extract multi-level intra-view features. Using the channel separation strategy, HAFEB can efficiently interact with the embedded cross-view interaction module. This structural configuration can efficiently mine features inside the view while improving the efficiency of cross-view information sharing. Hence, reconstruct image details and textures more accurately. Abundant experiments demonstrate the effectiveness of MFFSSR. We achieve superior performance with fewer parameters. The source code is available at https://github.com/KarosLYX/MFFSSR.