# Implicit Neural Representations for Deconvolving SAS Images

arXiv: https://arxiv.org/abs/2112.08539 · HTML: https://mlsanity.com/paper/2112.08539/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Neural Blind Deconvolution Using Deep Priors](https://mlsanity.com/paper/1908.02197/) (2019)
- [Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields](https://mlsanity.com/paper/2104.11745/) (2021)
- [CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems](https://mlsanity.com/paper/2102.05181/) (2021)
- [GPU Acceleration for Synthetic Aperture Sonar Image Reconstruction](https://mlsanity.com/paper/2101.05888/) (2021)

## Built on by (most cited first, 7 of 7)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar](https://mlsanity.com/paper/2306.09909/) (2023)
- [Radar Fields: An Extension of Radiance Fields to SAR](https://mlsanity.com/paper/2312.12961/) (2023)
- [Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Clouds](https://mlsanity.com/paper/2205.11480/) (2022)
- [NeST: Neural Stress Tensor Tomography by leveraging 3D Photoelasticity](https://mlsanity.com/paper/2406.10212/) (2024)
- [I-INR: Iterative Implicit Neural Representations](https://mlsanity.com/paper/2504.17364/) (2025)
- [NeRF-enabled Analysis-Through-Synthesis for ISAR Imaging of Small Everyday Objects with Sparse and Noisy UWB Radar Data](https://mlsanity.com/paper/2410.10085/) (2024)

## Abstract (arXiv)

Synthetic aperture sonar (SAS) image resolution is constrained by waveform bandwidth and array geometry. Specifically, the waveform bandwidth determines a point spread function (PSF) that blurs the locations of point scatterers in the scene. In theory, deconvolving the reconstructed SAS image with the scene PSF restores the original distribution of scatterers and yields sharper reconstructions. However, deconvolution is an ill-posed operation that is highly sensitive to noise. In this work, we leverage implicit neural representations (INRs), shown to be strong priors for the natural image space, to deconvolve SAS images. Importantly, our method does not require training data, as we perform our deconvolution through an analysis-bysynthesis optimization in a self-supervised fashion. We validate our method on simulated SAS data created with a point scattering model and real data captured with an in-air circular SAS. This work is an important first step towards applying neural networks for SAS image deconvolution.