Opt Lett. 2023 May 15;48(10):2740-2743. doi: 10.1364/OL.488562.
Recently, imaging systems have exhibited remarkable image restoration performance through optimized optical systems and deep-learning-based models. Despite advancements in optical systems and models, severe performance degradation occurs when the predefined optical blur kernel differs from the actual kernel while restoring and upscaling the images. This is because super-resolution (SR) models assume that a blur kernel is predefined and known. To address this problem, various lenses could be stacked, and the SR model could be trained with all available optical blur kernels. However, infinite optical blur kernels exist in reality; thus, this task requires the complexity of the lens, substantial model training time, and hardware overhead. To resolve this issue by focusing on the SR models, we propose a kernel-attentive weight modulation memory network by adaptively modulating SR weights according to the shape of the optical blur kernel. The modulation layers are incorporated into the SR architecture and dynamically modulate the weights according to the blur level. Extensive experiments reveal that the proposed method improves peak signal-to-noise ratio performance, with an average gain of 0.83 dB for blurred and downsampled images. An experiment with a real-world blur dataset demonstrates that the proposed method can handle real-world scenarios.
最近，通过优化的光学系统和基于深度学习的模型，成像系统在图像恢复方面表现出了显著的性能。尽管在光学系统和模型方面取得了进展，但在恢复和放大图像时，预定义的光学模糊核与实际核不同，性能会严重下降。这是因为超分辨率 (SR) 模型假设模糊核是预定义的且已知的。为了解决这个问题，可以堆叠各种镜头，并使用所有可用的光学模糊核来训练 SR 模型。然而，实际上存在无限数量的光学模糊核；因此，这项任务需要镜头的复杂性、大量的模型训练时间和硬件开销。为了通过关注 SR 模型来解决这个问题，我们提出了一种核感知权重调制记忆网络，通过根据光学模糊核的形状自适应地调制 SR 权重来解决这个问题。调制层被合并到 SR 架构中，并根据模糊程度动态地调制权重。广泛的实验表明，所提出的方法提高了峰值信噪比性能，对于模糊和下采样的图像，平均增益为 0.83 dB。使用真实模糊数据集的实验表明，所提出的方法可以处理真实场景。
