PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution

TL;DR

This paper introduces PFT-SSR, a Transformer-based model that leverages cross-view and intra-view information for stereo image super-resolution, achieving state-of-the-art performance.

Contribution

The paper proposes a novel Parallax Fusion Transformer with cross-view and intra-view modules, enhancing stereo image super-resolution beyond existing methods.

Findings

Outperforms most state-of-the-art methods

Achieves competitive super-resolution results

Demonstrates effectiveness of the Transformer-based architecture

Abstract

Stereo image super-resolution aims to boost the performance of image super-resolution by exploiting the supplementary information provided by binocular systems. Although previous methods have achieved promising results, they did not fully utilize the information of cross-view and intra-view. To further unleash the potential of binocular images, in this letter, we propose a novel Transformerbased parallax fusion module called Parallax Fusion Transformer (PFT). PFT employs a Cross-view Fusion Transformer (CVFT) to utilize cross-view information and an Intra-view Refinement Transformer (IVRT) for intra-view feature refinement. Meanwhile, we adopted the Swin Transformer as the backbone for feature extraction and SR reconstruction to form a pure Transformer architecture called PFT-SSR. Extensive experiments and ablation studies show that PFT-SSR achieves competitive results and outperforms most SOTA methods. Source code is available at https://github.com/MIVRC/PFT-PyTorch.