Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information
This work addresses the challenge of maintaining disparity consistency in stereo image enhancement for computer vision systems, representing an incremental improvement over single-image methods.
The paper tackles the problem of real-world stereo image super-resolution, where existing methods often disrupt disparity consistency. The proposed approach integrates a hybrid degradation model and an implicit stereo information discriminator to enhance images while preserving disparity, achieving impressive performance on synthetic and real datasets.
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}.