# DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy

arXiv: https://arxiv.org/abs/2605.13619 · HTML: https://mlsanity.com/paper/2605.13619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 3 of 3)

- [DiffuserCam: Lensless Single-exposure 3D Imaging](https://mlsanity.com/paper/1710.02134/) (2017)
- [Miniscope3D: optimized single-shot miniature 3D fluorescence microscopy](https://mlsanity.com/paper/2010.05382/) (2020)
- [Robust single-shot 3D fluorescence imaging in scattering media with a simulator-trained neural network](https://mlsanity.com/paper/2303.12573/) (2023)

## Abstract (arXiv)

Extended depth of field microscopy encodes axial information into a single acquisition through engineered point spread functions, but conventional and deep optics approaches are subject to degradation in scattering tissue. We introduce DeepFilters, a scattering-aware deep optics framework that jointly optimizes a parameterized pupil filter and a digital-filter-based reconstruction network through a calibrated differentiable forward model to achieve broad generalization without retraining. Incorporating empirical scattering kernels, physics-guided regularization, and a hybrid genetic-gradient initialization strategy, DeepFilters extends the PSF from 16 micron to >400 micron in clear media and enables signal recovery beyond 120 micron deep in biological tissues, validated across fixed brain slices and sea urchin embryos.