INTERNATIONAL JOURNAL OF RESEARCH CULTURE SOCIETY

Abstract: Stereo vision and image super-resolution (SR) are two fundamental areas in computer vision that have traditionally been addressed independently. Stereo vision aims to recover depth information by finding correspondences between two or more images, while super-resolution enhances the spatial resolution of an image. However, in real-world applications, limitations in sensor resolution often lead to a trade-off between field of view and image detail, adversely affecting the accuracy of depth estimation. Recently, there has been a growing interest in synergistically combining these two tasks to overcome their individual limitations. This survey provides a comprehensive overview of recent methods that integrate stereo vision with super-resolution. We categorize the existing approaches into sequential, concurrent, and deep learning-based frameworks. The literature survey explores key advancements, and a comparative analysis is presented based on critical evaluation parameters such as depth map accuracy, image quality metrics, and computational efficiency. The paper concludes by discussing open challenges and promising future research directions, highlighting the potential of end-to-end deep learning models to jointly optimize for both high-resolution imagery and precise depth estimation.        .