arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01349cs.CV
收藏

具有对齐注意力模块的双摄像机超分辨率

Dual-Camera Super-Resolution with Aligned Attention Modules

HKUST(香港科技大学);SenseTime Research(商汤科技研究院)

Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan, Qifeng Chen

摘要:

提出了一种基于参考图像的超分辨率(RefSR)方法,重点研究了双摄像头超分辨率(DCSR)方法,该方法利用参考图像获得高质量和高保真度的图像。我们提出的方法推广了标准的基于块的空间对齐操作的特征匹配。我们进一步探索了双摄像头超分辨率,这是RefSR的一个有前途的应用,并建立了一个数据集,由146个图像对从智能手机中的主摄像头和长焦摄像头。为了弥补真实世界图像和训练图像之间的领域差距,我们提出了一种用于真实世界图像的自监督领域自适应策略。在我们的数据集和公共基准上进行的大量实验表明,我们的方法在定量评估和视觉比较方面都比现有技术有了明显的改进。

英文摘要:

We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. We further explore the dual-camera super-resolution that is one promising application of RefSR, and build a dataset that consists of 146 image pairs from the main and telephoto cameras in a smartphone. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy for real-world images. Extensive experiments on our dataset and a public benchmark demonstrate clear improvement achieved by our method over state of the art in both quantitative evaluation and visual comparisons.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑