Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information

TL;DR

This paper introduces a novel stereo image super-resolution method that preserves disparity consistency in real-world scenarios by using a hybrid degradation model and an implicit stereo information discriminator.

Contribution

It proposes a hybrid degradation model combined with a stereo information discriminator to enhance stereo images while maintaining disparity consistency in real-world conditions.

Findings

Effective enhancement of stereo images on synthetic and real datasets

Preserves disparity consistency during super-resolution

Improves visual perception without degrading stereo disparity

Abstract

Real-world stereo image super-resolution has a significant influence on enhancing the performance of computer vision systems. Although existing methods for single-image super-resolution can be applied to improve stereo images, these methods often introduce notable modifications to the inherent disparity, resulting in a loss in the consistency of disparity between the original and the enhanced stereo images. To overcome this limitation, this paper proposes a novel approach that integrates a implicit stereo information discriminator and a hybrid degradation model. This combination ensures effective enhancement while preserving disparity consistency. The proposed method bridges the gap between the complex degradations in real-world stereo domain and the simpler degradations in real-world single-image super-resolution domain. Our results demonstrate impressive performance on synthetic and real datasets, enhancing visual perception while maintaining disparity consistency. The complete code is available at the following \href{https://github.com/fzuzyb/SCGLANet}{link}.