arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.03378cs.CV
收藏

相机镜头超分辨率

Camera Lens Super-Resolution

University of Science and Technology of China(中国科学技术大学)

Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha, Feng Wu

摘要:

用于单个图像超分辨率(SR)的现有方法通常用诸如双三次或高斯下采样的合成退化模型来评估。在本文中,我们从相机镜头的角度研究SR,命名为CameraSR,其目的是减轻现实成像系统中分辨率(R)和视场(V)之间的内在权衡。具体来说,我们将R-V退化视为SR过程中的一个潜在模型,并学习使用现实的低分辨率和高分辨率图像对来逆转它。为了获得成对的图像,我们提出了两种新颖的数据采集策略,用于两种代表性的成像系统(即,DSLR和智能手机相机)。基于获得的City 100数据集,我们定量分析了常用的综合退化模型的性能,并证明了CameraSR作为一种实用的解决方案,以提高现有SR方法的性能的优越性。此外,CameraSR可以很容易地推广到不同的内容和设备,这是一个先进的数字变焦工具,在现实的成像系统。代码和数据集可在https://github.com/ngchc/CameraSR上获得。

英文摘要:

Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we investigate SR from the perspective of camera lenses, named as CameraSR, which aims to alleviate the intrinsic tradeoff between resolution (R) and field-of-view (V) in realistic imaging systems. Specifically, we view the R-V degradation as a latent model in the SR process and learn to reverse it with realistic low- and high-resolution image pairs. To obtain the paired images, we propose two novel data acquisition strategies for two representative imaging systems (i.e., DSLR and smartphone cameras), respectively. Based on the obtained City100 dataset, we quantitatively analyze the performance of commonly-used synthetic degradation models, and demonstrate the superiority of CameraSR as a practical solution to boost the performance of existing SR methods. Moreover, CameraSR can be readily generalized to different content and devices, which serves as an advanced digital zoom tool in realistic imaging systems. Codes and datasets are available at https://github.com/ngchc/CameraSR.

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。

↑