# Neural Inverse Scattering with Score-based Regularization

arXiv: https://arxiv.org/abs/2505.14560 · HTML: https://mlsanity.com/paper/2505.14560/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 11 of 11)

- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields](https://mlsanity.com/paper/2104.11745/) (2021)
- [Provable Probabilistic Imaging using Score-Based Generative Priors](https://mlsanity.com/paper/2310.10835/) (2023)
- [Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields](https://mlsanity.com/paper/2112.00002/) (2021)
- [Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition](https://mlsanity.com/paper/2106.03668/) (2021)
- [Efficient and accurate inversion of multiple scattering with deep learning](https://mlsanity.com/paper/1803.06594/) (2018)
- [High-resolution 3D refractive index microscopy of multiple-scattering samples from intensity images](https://mlsanity.com/paper/1909.00023/) (2019)
- [Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems](https://mlsanity.com/paper/2407.09352/) (2024)
- [Efficient Inversion of Multiple-Scattering Model for Optical Diffraction Tomography](https://mlsanity.com/paper/1708.00745/) (2017)
- [SEAGLE: Sparsity-Driven Image Reconstruction under Multiple Scattering](https://mlsanity.com/paper/1705.04281/) (2017)
- [Accelerated Image Reconstruction for Nonlinear Diffractive Imaging](https://mlsanity.com/paper/1708.01663/) (2017)

## Built on by (most cited first, 1 of 1)

- [ScoreField: Neural Inverse Scattering with Score-Based Generative Priors](https://mlsanity.com/paper/2608.02937/) (2026)

## Abstract (arXiv)

Inverse scattering is a fundamental challenge in many imaging applications, ranging from microscopy to remote sensing. Solving this problem often requires jointly estimating two unknowns -- the image and the scattering field inside the object -- necessitating effective image prior to regularize the inference. In this paper, we propose a regularized neural field (NF) approach which integrates the denoising score function used in score-based generative models. The neural field formulation offers convenient flexibility to performing joint estimation, while the denoising score function imposes the rich structural prior of images. Our results on three high-contrast simulated objects show that the proposed approach yields a better imaging quality compared to the state-of-the-art NF approach, where regularization is based on total variation.