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

arXiv: https://arxiv.org/abs/2407.09525 · HTML: https://mlsanity.com/paper/2407.09525/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups](https://mlsanity.com/paper/2005.11621/) (2020)
- [Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation](https://mlsanity.com/paper/2010.04865/) (2020)
- [Adversarial Autoencoders for Compact Representations of 3D Point Clouds](https://mlsanity.com/paper/1811.07605/) (2018)
- [A Generative deep learning approach for shape recognition of arbitrary objects from phaseless acoustic scattering data](https://mlsanity.com/paper/2207.05433/) (2022)
- [Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding](https://mlsanity.com/paper/2105.08177/) (2021)
- [Fast acoustic scattering using convolutional neural networks](https://mlsanity.com/paper/1911.01802/) (2019)
- [Laplace-Beltrami based Multi-Resolution Shape Reconstruction on Subdivision Surfaces](https://mlsanity.com/paper/2104.04027/) (2021)

## Abstract (arXiv)

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.