DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917491615203328 |
|---|---|
| author | Greene, Joseph L. Chan, Suet YIng Deng, Qilin Alido, Jeffrey Lion, Alexandra Hu, Guorong Guo, Ruipeng Li, Tongyu Kiliç, Kivilcim Davison, Ian Tian, Lei |
| author_facet | Greene, Joseph L. Chan, Suet YIng Deng, Qilin Alido, Jeffrey Lion, Alexandra Hu, Guorong Guo, Ruipeng Li, Tongyu Kiliç, Kivilcim Davison, Ian Tian, Lei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13619 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy Greene, Joseph L. Chan, Suet YIng Deng, Qilin Alido, Jeffrey Lion, Alexandra Hu, Guorong Guo, Ruipeng Li, Tongyu Kiliç, Kivilcim Davison, Ian Tian, Lei Optics Computer Vision and Pattern Recognition 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. |
| title | DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy |
| topic | Optics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.13619 |