← 研踪 PaperTrailarXiv:2610.40088 · v1
Neural Blind Deconvolution for Image Scanning Microscopy
首次提交 2026-10-29 21:57
版本更新 2026-10-29 21:57
雷达观测 2026-10-30 13:28
摘要
Image scanning microscopy (ISM) acquires one scanned image per detector element, which are then fused into a single image by multi-image deconvolution to obtain a super-resolved image. Its accuracy, however, depends on point spread function (PSF) models that sample- and system-induced aberrations often invalidate. Since differences between the scanned images encode aberration information, we propose a training-free blind Deep Image Prior (DIP) framework that jointly estimates the specimen and the detector-dependent PSFs. The PSFs are parametrised through the detector geometry and shared excitation and emission PSFs, reducing the unknowns while preserving the physical ISM model, and a Gaussian pre-initialisation stabilises the blind optimisation. On experimental tubulin data, blind DIP recovers finer filamentous structures than multi-image deconvolution and DIP with fixed theoretical PSFs, while adapting the PSFs to the measurements.
作者备注：4 pages, 2 figures
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-29 21:57 · 最新观测版本
Neural Blind Deconvolution for Image Scanning Microscopy
Image scanning microscopy (ISM) acquires one scanned image per detector element, which are then fused into a single image by multi-image deconvolution to obtain a super-resolved image. Its accuracy, however, depends on point spread function (PSF) models that sample- and system-induced aberrations often invalidate. Since differences between the scanned images encode aberration information, we propose a training-free blind Deep Image Prior (DIP) framework that jointly estimates the specimen and the detector-dependent PSFs. The PSFs are parametrised through the detector geometry and shared excitation and emission PSFs, reducing the unknowns while preserving the physical ISM model, and a Gaussian pre-initialisation stabilises the blind optimisation. On experimental tubulin data, blind DIP recovers finer filamentous structures than multi-image deconvolution and DIP with fixed theoretical PSFs, while adapting the PSFs to the measurements.
查看此版本解读 →查看此版本原文 ↗