Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations without storing intermediate activation values. However, the dependence of the computational/memory complexity of the measurement models in PnP/RED on the total number of measurements leaves DEQ impractical for many imaging applications. We propose ODER as a new strategy for improving the efficiency of DEQ through stochastic approximations of the measurement models. We theoretically analyze ODER giving insights into its convergence and ability to approximate the traditional DEQ approach. Our numerical results suggest the potential improvements in training/testing complexity due to ODER on three distinct imaging applications.
翻译:虽然传统的PnP/RED配方侧重于使用图像Demoisers指定的前科,但人们日益关注最终至最终最佳的PnP/RED前科学习PnP/RED, 最近的深平衡模型(DEQ)框架通过不储存中间激活值的固定点方程式,通过对固定点方程式进行隐含的区分,解决成像反问题。然而,PnP/RED的计量模型的计算/模拟复杂性取决于测量的总数,使得DEQ对许多成像应用不切实际。我们建议ODER作为通过测量模型的随机近似来提高DEQ效率的新战略。我们从理论上分析ODER,了解其趋近于传统的DEQ方法的趋同和能力。我们的数字结果显示,由于对ODER的三种不同应用,在培训/测试复杂性方面可能有所改进。