Super-resolution (SR) aims to increase the resolution of imagery. Applications include security, medical imaging, and object recognition. We propose a deep learning-based SR system that takes a hexagonally sampled low-resolution image as an input and generates a rectangularly sampled SR image as an output. For training and testing, we use a realistic observation model that includes optical degradation from diffraction and sensor degradation from detector integration. Our SR approach first uses nonuniform interpolation to partially upsample the observed hexagonal imagery and convert it to a rectangular grid. We then leverage a state-of-the-art convolutional neural network architecture designed for SR known as residual channel attention network (RCAN). In particular, we use RCAN to further upsample and restore the imagery to produce the final SR image estimate. We demonstrate that this system is superior to applying RCAN directly to rectangularly sampled LR imagery with equivalent sample density. The theoretical advantages of hexagonal sampling are well known. However, to the best of our knowledge, the practical benefit of hexagonal sampling in light of modern processing techniques such as RCAN SR is heretofore untested. Our SR system demonstrates a notable advantage of hexagonally sampled imagery when employing a modified RCAN for hexagonal SR.

中文翻译：

---

使用深度学习对六边形采样图像进行重采样和超分辨率

超分辨率 (SR) 旨在提高图像的分辨率。应用包括安全、医学成像和物体识别。我们提出了一种基于深度学习的 SR 系统，该系统以六边形采样的低分辨率图像作为输入，并生成矩形采样的 SR 图像作为输出。对于训练和测试，我们使用了一个真实的观察模型，其中包括衍射引起的光学退化和探测器集成引起的传感器退化。我们的 SR 方法首先使用非均匀插值对观察到的六边形图像进行部分上采样并将其转换为矩形网格。然后，我们利用为 SR 设计的最先进的卷积神经网络架构，称为残差通道注意网络 (RCAN)。特别是，我们使用 RCAN 进一步上采样和恢复图像以产生最终的 SR 图像估计。我们证明该系统优于将 RCAN 直接应用于具有等效样本密度的矩形采样 LR 图像。六边形采样的理论优势是众所周知的。然而，据我们所知，鉴于 RCAN SR 等现代处理技术，六边形采样的实际好处迄今为止尚未经过测试。当对六边形 SR 使用改进的 RCAN 时，我们的 SR 系统展示了六边形采样图像的显着优势。鉴于 RCAN SR 等现代处理技术，六边形采样的实际优势迄今为止尚未经过测试。当对六边形 SR 使用改进的 RCAN 时，我们的 SR 系统展示了六边形采样图像的显着优势。鉴于 RCAN SR 等现代处理技术，六边形采样的实际优势迄今为止尚未经过测试。当对六边形 SR 使用改进的 RCAN 时，我们的 SR 系统展示了六边形采样图像的显着优势。