光子受限去卷积的结构化核估计
Structured Kernel Estimation for Photon-Limited Deconvolution
AI总结：
针对低光照下相机抖动导致的运动模糊与光子散粒噪声问题，提出一种基于梯度的模糊核估计技术，利用运动轨迹关键点的低维表示缩小搜索空间并提升正则性，在迭代框架中实现了优于端到端神经网络去卷积性能。
摘要：
在低光照条件下拍摄的图像，若伴随相机抖动，会受运动模糊和光子散粒噪声的影响。尽管最先进的图像恢复网络表现出良好的效果，但它们大多局限于光照充足的场景，当光子散粒噪声较强时，其性能会显著下降。本文提出了一种专为光子受限条件设计的新型模糊估计技术。该方法采用基于梯度的反向传播方法来估计模糊核。通过使用运动轨迹上的关键点对模糊核进行低维表示建模，我们显著缩小了搜索空间，并提升了核估计问题的正则性。当接入迭代框架时，我们新颖的低维表示提供了改进的核估计，因此与端到端训练的神经网络相比，具有显著更好的去卷积性能。源代码和预训练模型可在 \url{https://github.com/sanghviyashiitb/structured-kernel-cvpr23} 获取。
英文摘要：
Images taken in a low light condition with the presence of camera shake suffer from motion blur and photon shot noise. While state-of-the-art image restoration networks show promising results, they are largely limited to well-illuminated scenes and their performance drops significantly when photon shot noise is strong. In this paper, we propose a new blur estimation technique customized for photon-limited conditions. The proposed method employs a gradient-based backpropagation method to estimate the blur kernel. By modeling the blur kernel using a low-dimensional representation with the key points on the motion trajectory, we significantly reduce the search space and improve the regularity of the kernel estimation problem. When plugged into an iterative framework, our novel low-dimensional representation provides improved kernel estimates and hence significantly better deconvolution performance when compared to end-to-end trained neural networks. The source code and pretrained models are available at \url{https://github.com/sanghviyashiitb/structured-kernel-cvpr23}
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。
