论文标题
NAFSSR：使用NAFNET的立体声图像超分辨率
NAFSSR: Stereo Image Super-Resolution Using NAFNet
论文作者
论文摘要
立体图像超分辨率旨在通过利用双目系统提供的互补信息来提高超分辨率结果的质量。为了获得合理的性能，大多数方法都专注于设计模块，损失功能等，以从另一个角度利用信息。这具有提高系统复杂性的副作用，使研究人员难以评估新想法并比较方法。本文继承了一个强大而简单的图像恢复模型NAFNET，用于单视特征提取，并通过将交叉注意模块添加到视图之间的融合特征来适应双眼场景来扩展它。立体声图像超分辨率的提议的基线被认为是NAFSSR。此外，提出了培训/测试策略，以充分利用NAFSSR的性能。广泛的实验证明了我们方法的有效性。特别是，NAFSSR的表现优于Kitti 2012，Kitti 2015，Middlebury和Flickr1024数据集的最新方法。借助NAFSSR，我们在NTIRE 2022立体声图像超分辨率挑战中赢得了第一名。代码和模型将在https://github.com/megvii-research/nafnet上发布。
Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems. To obtain reasonable performance, most methods focus on finely designing modules, loss functions, and etc. to exploit information from another viewpoint. This has the side effect of increasing system complexity, making it difficult for researchers to evaluate new ideas and compare methods. This paper inherits a strong and simple image restoration model, NAFNet, for single-view feature extraction and extends it by adding cross attention modules to fuse features between views to adapt to binocular scenarios. The proposed baseline for stereo image super-resolution is noted as NAFSSR. Furthermore, training/testing strategies are proposed to fully exploit the performance of NAFSSR. Extensive experiments demonstrate the effectiveness of our method. In particular, NAFSSR outperforms the state-of-the-art methods on the KITTI 2012, KITTI 2015, Middlebury, and Flickr1024 datasets. With NAFSSR, we won 1st place in the NTIRE 2022 Stereo Image Super-resolution Challenge. Codes and models will be released at https://github.com/megvii-research/NAFNet.
