论文标题
立体声图像超分辨率的对称视差关注
Symmetric Parallax Attention for Stereo Image Super-Resolution
论文作者
论文摘要
尽管近年来见证了立体声超级分辨率（SR）的巨大进步，但双目系统提供的有益信息尚未得到充分使用。由于立体声图像在表现约束下高度对称，因此在本文中，我们通过利用立体声图像对中的对称提示来提高立体声图像SR的性能。具体而言，我们提出了一种对称双向视差注意模块（BIPAM）和一个内联遮挡处理方案，以有效地相互交互。然后，我们以高度对称的方式设计了一个配备BIPAM的暹罗网络，以超级溶解视图的两面。最后，我们设计了几种启发性损失，以提高立体声的一致性。四个公共数据集的实验证明了我们方法的出色性能。源代码可从https://github.com/yingqianwang/ipassr获得。
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.
