Symmetric Parallax Attention for Stereo Image Super-Resolution

2020/11/07 by Yingqian Wang, Wang, Yingqian, Xinyi Ying +9 · 2 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques

paper · pdf · doi:10.48550/arxiv.2011.03802

openalex publication_date 2020/11/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Although recent years have witnessed the great advances in stereo image super-resolution (SR), the beneficial information provided by binocular systems has not been fully used. Since stereo images are highly symmetric under epipolar constraint, in this paper, we improve the performance of stereo image SR by exploiting symmetry cues in stereo image pairs. Specifically, we propose a symmetric bi-directional parallax attention module (biPAM) and an inline occlusion handling scheme to effectively interact cross-view information. Then, we design a Siamese network equipped with a biPAM to super-resolve both sides of views in a highly symmetric manner. Finally, we design several illuminance-robust losses to enhance stereo consistency. Experiments on four public datasets demonstrate the superior performance of our method. Source code is available at https://github.com/YingqianWang/iPASSR.

Citations

• No-Reference Image Quality Assessment in the Spatial Domain
• Detail-revealing Deep Video Super-resolution
• Residual Non-local Attention Networks for Image Restoration
• Image Super-Resolution by Neural Texture Transfer
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
• Deformable 3D Convolution for Video Super-Resolution
• Learning Texture Transformer Network for Image Super-Resolution

Cited by

• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• SNNSIR: A Simple Spiking Neural Network for Stereo Image Restoration

Related

• Learning Parallax Attention for Stereo Image Super-Resolution
• Parallax Attention for Unsupervised Stereo Correspondence Learning
• Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention
• StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation
• Cross-View Hierarchy Network for Stereo Image Super-Resolution