Optical microscopy image plays an important role in scientific research
through the direct visualization of the nanoworld, where the imaging mechanism
is described as the convolution of the point spread function (PSF) and
emitters. Based on a priori knowledge of the PSF or equivalent PSF, it is
possible to achieve more precise exploration of the nanoworld. However, it is
an outstanding challenge to directly extract the PSF from microscopy images.
Here, with the help of self-supervised learning, we propose a physics-informed
masked autoencoder (PiMAE) that enables a learnable estimation of the PSF and
emitters directly from the raw microscopy images. We demonstrate our method in
synthetic data and real-world experiments with significant accuracy and noise
robustness. PiMAE outperforms DeepSTORM and the Richardson-Lucy algorithm in
synthetic data tasks with an average improvement of 19.6\% and 50.7\% (35
tasks), respectively, as measured by the normalized root mean square error
(NRMSE) metric. This is achieved without prior knowledge of the PSF, in
contrast to the supervised approach used by DeepSTORM and the known PSF
assumption in the Richardson-Lucy algorithm. Our method, PiMAE, provides a
feasible scheme for achieving the hidden imaging mechanism in optical
microscopy and has the potential to learn hidden mechanisms in many more
systems.

利用自监督学习，提出一种物理信息掩蔽自动编码器 (PiMAE)，能够通过直接从原始显微图像中学习估计点扩散函数 (PSF) 和发射源的值，这种方法优于传统方法，展示了可行的机制实现在光学显微镜中实现更精确的成像。

直接从光学显微观测中学习成像机理

Learning imaging mechanism directly from optical microscopy observations

High quality imaging usually requires bulky and expensive lenses to
compensate geometric and chromatic aberrations. This poses high constraints on
the optical hash or low cost applications. Although one can utilize algorithmic
reconstruction to remove the artifacts of low-end lenses, the degeneration from
optical aberrations is spatially varying and the computation has to trade off
efficiency for performance. For example, we need to conduct patch-wise
optimization or train a large set of local deep neural networks to achieve high
reconstruction performance across the whole image. In this paper, we propose a
PSF aware plug-and-play deep network, which takes the aberrant image and PSF
map as input and produces the latent high quality version via incorporating
lens-specific deep priors, thus leading to a universal and flexible optical
aberration correction method. Specifically, we pre-train a base model from a
set of diverse lenses and then adapt it to a given lens by quickly refining the
parameters, which largely alleviates the time and memory consumption of model
learning. The approach is of high efficiency in both training and testing
stages. Extensive results verify the promising applications of our proposed
approach for compact low-end cameras.

本文提出了一种 PSF 感知的即插即用深度网络，通过引入特定镜头的深度先验知识，以消除光学像差，从而实现了通用和灵活的光学像差校正方法，该方法具有高效的性能。

基于深度先验的通用灵活光学像差校正

Universal and Flexible Optical Aberration Correction Using Deep-Prior  Based Deconvolution

The weak-lensing science of the LSST project drives the need to carefully
model and separate the instrumental artifacts from the intrinsic lensing
signal. The dominant source of the systematics for all ground based telescopes
is the spatial correlation of the PSF modulated by both atmospheric turbulence
and optical aberrations. In this paper, we present a full FOV simulation of the
LSST images by modeling both the atmosphere and the telescope optics with the
most current data for the telescope specifications and the environment. To
simulate the effects of atmospheric turbulence, we generated six-layer phase
screens with the parameters estimated from the on-site measurements. For the
optics, we combined the ray-tracing tool ZEMAX and our simulated focal plane
data to introduce realistic aberrations and focal plane height fluctuations.
Although this expected flatness deviation for LSST is small compared with that
of other existing cameras, the fast f-ratio of the LSST optics makes this focal
plane flatness variation and the resulting PSF discontinuities across the CCD
boundaries significant challenges in our removal of the systematics. We resolve
this complication by performing PCA CCD-by-CCD, and interpolating the basis
functions using conventional polynomials. We demonstrate that this PSF
correction scheme reduces the residual PSF ellipticity correlation below 10^-7
over the cosmologically interesting scale. From a null test using HST/UDF
galaxy images without input shear, we verify that the amplitude of the galaxy
ellipticity correlation function, after the PSF correction, is consistent with
the shot noise set by the finite number of objects. Therefore, we conclude that
the current optical design and specification for the accuracy in the focal
plane assembly are sufficient to enable the control of the PSF systematics
required for weak-lensing science with the LSST.

本文介绍一种用于减少地基望远镜系统性误差的 PSF 校正方案，通过零测试，证明 PSF 校正方案可以满足 LSST 弱引力透镜科学所需的系统性误差控制精度。