A Deep Learning Framework for Three Dimensional Shape Reconstruction from Phaseless Acoustic Scattering Far-field Data

TL;DR

This paper introduces a deep learning framework that reconstructs 3D shapes from limited phaseless acoustic scattering data using a variational auto-encoder and CNN, achieving accurate results on complex datasets.

Contribution

It presents a novel deep learning approach combining a variational auto-encoder and CNN for 3D shape reconstruction from minimal acoustic data.

Findings

Accurately reconstructs complex 3D shapes like airplanes and automobiles.

Works effectively with limited, phase-less far-field data.

Demonstrates robustness across diverse datasets.

Abstract

The inverse scattering problem is of critical importance in a number of fields, including medical imaging, sonar, sensing, non-destructive evaluation, and several others. The problem of interest can vary from detecting the shape to the constitutive properties of the obstacle. The challenge in both is that this problem is ill-posed, more so when there is limited information. That said, significant effort has been expended over the years in developing solutions to this problem. Here, we use a different approach, one that is founded on data. Specifically, we develop a deep learning framework for shape reconstruction using limited information with single incident wave, single frequency, and phase-less far-field data. This is done by (a) using a compact probabilistic shape latent space, learned by a 3D variational auto-encoder, and (b) a convolutional neural network trained to map the acoustic scattering information to this shape representation. The proposed framework is evaluated on a synthetic 3D particle dataset, as well as ShapeNet, a popular 3D shape recognition dataset. As demonstrated via a number of results, the proposed method is able to produce accurate reconstructions for large batches of complex scatterer shapes (such as airplanes and automobiles), despite the significant variation present within the data.