• Corpus ID: 235293928

Accurate and Robust Deep Learning Framework for Solving Wave-Based Inverse Problems in the Super-Resolution Regime

@article{Li2021AccurateAR,
  title={Accurate and Robust Deep Learning Framework for Solving Wave-Based Inverse Problems in the Super-Resolution Regime},
  author={Matthew Li and Laurent Demanet and Leonardo Zepeda-N'unez},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.01143}
}
We propose an end-to-end deep learning framework that comprehensively solves the inverse wave scattering problem across all length scales. Our framework consists of the newly introduced wide-band butterfly network [37] coupled with a simple training procedure which dynamically injects noise during training. While our trained network provides competitive results in classical imaging regimes, most notably it also succeeds in the super-resolution regime where other comparable methods fail. This… 

References

SHOWING 1-10 OF 56 REFERENCES
Solving Inverse Wave Scattering with Deep Learning
TLDR
A neural network approach for solving two classical problems in the two-dimensional inverse wave scattering: far field pattern problem and seismic imaging using the recently introduced BCR-Net along with the standard convolution layers.
SwitchNet: a neural network model for forward and inverse scattering problems
TLDR
A novel neural network architecture, SwitchNet, is proposed for solving the wave equation based inverse scattering problems via providing maps between the scatterers and the scattered field (and vice versa) by leveraging the inherent low-rank structure of the scattering problems and introducing a novel switching layer with sparse connections.
Solving Traveltime Tomography with Deep Learning
TLDR
This paper proposes an effective neural network architecture for the inverse map using the recently proposed BCR-Net, with weights learned from training datasets, and demonstrates the efficiency of the proposed neural networks.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Dynamical machine learning volumetric reconstruction of objects’ interiors from limited angular views
TLDR
The dynamic method is suitable for a generic interior-volumetric reconstruction under a limited-angle scheme and accurately reconstructs volume interiors under two conditions: weak scattering, when the Radon transform approximation is applicable and the forward operator well defined; and strong scattering, which is nonlinear with respect to the 3D refractive index distribution and includes uncertainty in the forward operators.
A multiscale neural network based on hierarchical nested bases
In recent years, deep learning has led to impressive results in many fields. In this paper, we introduce a multiscale artificial neural network for high-dimensional nonlinear maps based on the idea
An overview of full-waveform inversion in exploration geophysics
TLDR
This review attempts to illuminate the state of the art of FWI by building accurate starting models with automatic procedures and/or recording low frequencies, and improving computational efficiency by data-compression techniquestomake3DelasticFWIfeasible.
Physics-informed neural networks for inverse problems in nano-optics and metamaterials.
TLDR
The emerging paradigm of physics-informed neural networks (PINNs) are employed for the solution of representative inverse scattering problems in photonic metamaterials and nano-optics technologies and successfully apply mesh-free PINNs to the difficult task of retrieving the effective permittivity parameters of a number of finite-size scattering systems.
High Resolution Inverse Scattering in Two Dimensions Using Recursive Linearization
TLDR
A fast, stable algorithm for the solution of the inverse acoustic scattering problem in two dimensions, using Chen's method of recursive linearization to reconstruct an unknown sound speed at resolutions of thousands of square wavelengths in a fully nonlinear regime.
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
TLDR
Butterfly-net, a low-complexity CNN with structured and sparse across-channel connections, which aims at an optimal hierarchical function representation of the input signal, outperforms the hard-coded Butterfly-net and achieves similar accuracy as the trained CNN but with much less parameters.
...
1
2
3
4
5
...