Photon Limited Non-Blind Deblurring Using Algorithm Unrolling
Photon Limited Non-Blind Deblurring Using Algorithm Unrolling
复制标题
DOI：
10.1109/tci.2022.3209939
复制
发表时间：
2022-01-01
影响因子：
5.4
通讯作者：
Chan, Stanley H.
中科院分区：
文献类型：
--
作者：
Sanghvi, Yash;Gnanasambandam, Abhiram;Chan, Stanley H.
在诸如摄影、显微镜和天文学等各种微光应用中，光子受限条件下的图像去模糊普遍存在。然而，由于低照度和/或短曝光导致的光子散粒噪声的存在使得去模糊任务比传统的去模糊问题更具挑战性。在这篇文章中，我们提出了一种算法展开方法，通过在固定的迭代次数下展开即插即用算法来解决光子受限去模糊问题。通过引入即插即用框架的三算子分裂形式，我们得到了一系列可微步骤，允许固定迭代展开网络进行端到端的训练。与现有的最先进的去模糊方法相比，所提出的算法具有明显更好的图像恢复效果。我们还提出了一个新的光子受限去模糊数据集来评估算法的性能。
Image deblurring in photon-limited conditions is ubiquitous in a variety of low-light applications such as photography, microscopy and astronomy. However, the presence of the photon shot noise due to the low illumination and/or short exposure makes the deblurring task substantially more challenging than the conventional deblurring problems. In this paper, we present an algorithm unrolling approach for the photon-limited deblurring problem by unrolling a Plug-and-Play algorithm for a fixed number of iterations. By introducing a three-operator splitting formation of the Plug-and-Play framework, we obtain a series of differentiable steps which allows the fixed iteration unrolled network to be trained end-to-end. The proposed algorithm demonstrates significantly better image recovery compared to existing state-of-the-art deblurring approaches. We also present a new photon-limited deblurring dataset for evaluating the performance of algorithms.