Perception-Oriented Stereo Image Super-Resolution
This work addresses the need for better visual quality in StereoSR for applications like disparity estimation, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of stereo image super-resolution (StereoSR) by focusing on improving perceptual quality rather than just quantitative metrics, resulting in a method that significantly enhances visual quality and reliability for disparity estimation.
Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR. However, existing StereoSR models mainly concentrate on improving quantitative evaluation metrics and neglect the visual quality of super-resolved stereo images. To improve the perceptual performance, this paper proposes the first perception-oriented stereo image super-resolution approach by exploiting the feedback, provided by the evaluation on the perceptual quality of StereoSR results. To provide accurate guidance for the StereoSR model, we develop the first special stereo image super-resolution quality assessment (StereoSRQA) model, and further construct a StereoSRQA database. Extensive experiments demonstrate that our StereoSR approach significantly improves the perceptual quality and enhances the reliability of stereo images for disparity estimation.