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

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 furt...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Guo, Hansheng, Li, Juncheng, Gao, Guangwei, Li, Zhi, Zeng, Tieyong
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 24.03.2023
Subjects
Ablation
Computer Science - Computer Vision and Pattern Recognition
Feature extraction
Image resolution
Parallax
Source code
Transformers
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2303.13807