TL;DR这篇文章提出了一种基于 Deep Equilibrium Models 的方案,通过无限循环的迭代,不断提高图像逆问题的重建精度,同时在测试时可以根据不同场景的需求选择不同的计算预算以优化精度和计算的权衡。
Abstract
Recent efforts on solving inverse problems in imaging via deep neural
networks use architectures inspired by a fixed number of iterations of an
optimization method. The number of iterations is typically quite small due to
difficulties in training networks corresponding to more iteratio