Neural networks have recently allowed solving many ill-posed inverse problems with unprecedented performance. Physics informed approaches already progressively replace carefully hand-crafted reconstruction algorithms in real applications. However, these networks suffer from a major defect: when trained on a given forward operator, they do not generalize well to a different one. The aim of this paper is twofold. First, we show through various applications that training the network with a family of forward operators allows solving the adaptivity problem without compromising the reconstruction quality significantly. Second, we illustrate that this training procedure allows tackling challenging blind inverse problems. Our experiments include partial Fourier sampling problems arising in magnetic resonance imaging (MRI), computerized tomography (CT) and image deblurring.
翻译:物理知情的方法已经在实际应用中逐渐取代了精心手工设计的重建算法。然而,这些网络存在一个重大缺陷:当在某个前方操作器上接受培训时,它们并不向不同的操作器推广。本文的目的是双重的。首先,我们通过各种应用方法表明,通过一个由远方操作器组成的网络培训能够解决适应性问题,同时又不会显著地损害重建质量。第二,我们说明,这种培训程序可以解决挑战性的盲面反问题。我们的实验包括磁共振成像(MRI)、计算机成像(CT)和图像破碎(图像)中出现的部分Fourier抽样问题。