论文标题
单调收敛正则化。
Monotonically Convergent Regularization by Denoising
论文作者
论文摘要
通过denoing（红色）正规化是一个广泛使用的框架，用于通过利用图像Deoisiser作为图像先验来解决反问题。最近的工作报道了红色在许多成像应用中的最新性能，使用预先训练的深神经网作为Denoisers。尽管取得了最近的进展，但红色算法的稳定收敛仍然是一个开放的问题。现有的红色理论仅保证了凸数据限制项和非专业授权者的稳定性。这项工作通过开发一种新的单调红色（MRED）算法来解决这个问题，该算法的融合不需要先前的深层denoising。即使传统的红色算法散开，也从随机矩阵上进行的图像脱张和从随机矩阵中恢复的压缩感测恢复的模拟显示出MRD的稳定性。
Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the state-of-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers. Despite the recent progress, the stable convergence of RED algorithms remains an open problem. The existing RED theory only guarantees stability for convex data-fidelity terms and nonexpansive denoisers. This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior. Simulations on image deblurring and compressive sensing recovery from random matrices show the stability of MRED even when the traditional RED algorithm diverges.
