论文标题
学习基于波的成像的几何形状
Learning the geometry of wave-based imaging
论文作者
论文摘要
我们为基于波浪的成像问题提出了一个基于物理学的一般深度学习体系结构。具有不同背景波速度的成像问题的关键困难是，介质根据其位置和方向“弯曲”波浪的“弯曲”不同。这种空间弯曲的几何形状使与卷积网络的翻译具有不良感应偏置。我们构建了一个可解释的神经体系结构，灵感来自傅立叶积分运算符（FIO），该操作员（FIO）近似波浪物理学。 FIOS模拟各种成像方式，从地震学和雷达到多普勒和超声。我们专注于通过基于最佳运输的损失来学习FIO捕获的波传播的几何形状，该波动传播的几何形状。在许多成像逆问题上，尤其是在分布外测试中，提出的fionet的性能明显优于常规基线。
We propose a general physics-based deep learning architecture for wave-based imaging problems. A key difficulty in imaging problems with a varying background wave speed is that the medium "bends" the waves differently depending on their position and direction. This space-bending geometry makes the equivariance to translations of convolutional networks an undesired inductive bias. We build an interpretable neural architecture inspired by Fourier integral operators (FIOs) which approximate the wave physics. FIOs model a wide range of imaging modalities, from seismology and radar to Doppler and ultrasound. We focus on learning the geometry of wave propagation captured by FIOs, which is implicit in the data, via a loss based on optimal transport. The proposed FIONet performs significantly better than the usual baselines on a number of imaging inverse problems, especially in out-of-distribution tests.
