Tiếng Việt

Unsupervised physical neural network empowers stacked imaging denoising algorithm

903
2025-03-25 15:23:55
Xem bản dịch

In view of the reconstruction problem of stack imaging technology in noisy environment, Lin Nan's team from Shanghai Institute of Optics and Mechanics, Chinese Academy of Sciences, proposed an innovative method ProPtyNet based on unsupervised physical neural network, which is expected to be applied to chip CD measurement and defect detection. The article was published in Optics and lasers in engineering under the title of "Noise robust photography using unsupervised natural network".
Its core innovations and achievements are as follows:

1. Core issues and challenges
Stacked imaging uses diffraction patterns to invert the complex amplitude distribution of objects, but faces challenges in the following scenarios:
Complex noise environment: Poisson noise (signal-to-noise ratio 24.64dB) under low light conditions and mixed noise caused by random high-energy particles can lead to the failure of traditional algorithms
Dynamic bandwidth imaging: Non monochromatic light sources make non target wavelengths a new frequency domain noise source
Hardware limitations: Traditional iterative algorithms are slow and difficult to achieve fast imaging.

2. Method innovation
Propose a dual driven framework of "physical model+deep learning"
Data processing architecture: Zero padding preprocessing (e.g. 512 → 612 pixels) and four component output (amplitude/phase x object/probe) are used to improve axial resolution
Network topology optimization: Customize U-net architecture (with only 2.5 million parameters) to achieve four-dimensional parameter joint optimization, and extend the dynamic range of the "Conv2d tanh" phase layer to 2 π
Anti noise loss function: pioneering a dual loss mechanism (β=0.85-0.95) to balance overexposed areas (γ=1 → 0.1 gradient) and probe structured constraints, resulting in a 5-fold decrease in loss function

3. Experimental verification
Verify performance through 600 sets of tests:
Noise robustness: Under mixed noise (SNR 30dB), the SSIM value reaches 0.92 ± 0.03, which is about 14 times higher than ePIE
Speed advantage: The single convergence time is 729 seconds, which is 47.8% and 31.9% faster than AD and ePIE, respectively
Wide spectral adaptability: effectively separates ± 5nm noise components in the 405nm band, achieving a resolution of 57 line pairs/mm

4. Application prospects
Extreme Ultraviolet EUV Imaging: The method has been adapted to the Fresnel propagation model and can be extended to a wavelength of 13.5nm
Low dose dynamic monitoring: Effective suppression of readout noise under 300 μ s short exposure conditions (NPS=0.12)
Multi parameter joint calibration: achieving joint calibration along the axis (zPIE) and oblique incidence (aPIE) by adding output channels [35-36]
This study provides a breakthrough in both computer principles and experimental models for coherent imaging of new light sources (X-ray/EUV) and extreme operating conditions (low temperature/irradiation).


Figure 1. ProPtyNet algorithm details. (a) ProPtyNet network flowchart. (b) Details of U-net network architecture. (c) Data preprocessing and post-processing methods.


Figure 2. Simulation reconstruction results. (a) The true amplitude and phase of objects and probes. (b) The reconstruction results of ProPtyNet, ePIE, rPIE, and AD algorithms under Poisson noise, Gaussian noise, and mixed noise.


Figure 3. Experimental results. (a) The reconstruction results of sample amplitude information under different noise environments. (b) Comparison of amplitude cross-sections in the underlined section. (c) Comparison of loss functions in the iterative process.


Figure 4. Reconstruction results under broad-spectrum illumination (a) Experimental illumination light spectrum. (b) Simulation and experimental results.

Source: opticsky

Đề xuất liên quan
  • The First Operation of Two Color Mode in Infrared Free Electron Laser

    The Fritz Haber Institute of the Max Planck Institute in Berlin has achieved a technological milestone. The infrared free electron laser operates in dual color mode for the first time. This globally unique technology makes it possible to conduct experiments on synchronous dual color laser pulses, opening up new possibilities for research.There are over a dozen free electron lasers worldwide, with ...

    2024-02-18
    Xem bản dịch
  • The birth of multi photon 3D laser printing technology: printing millions of particles within 1 second

    Multi photon 3D laser printing technology, as a disruptive micro manufacturing technology, is facing two major challenges: speed and material compatibility. However, the latest research has made breakthrough progress, successfully increasing printing speed tenfold while maintaining excellent detail accuracy.In this remarkable study, scientists abandoned the traditional single beam printing method ...

    2024-04-19
    Xem bản dịch
  • Surface coupled laser technology manufacturer, secured £ 2.94 million in financing

    Recently, renowned surface coupled laser technology supplier Vector Photonics announced that it has received £ 1.667 million in equity investment and £ 1.27 million in additional research funding for the continued commercialization of its unique surface coupled laser (SCL) technology. Surface coupled lasers have completely changed semiconductor laser manufacturing, improving the performance of var...

    2024-06-14
    Xem bản dịch
  • Shanghai Institute of Optics and Mechanics proposes a new scheme of Er doped silicate fiber as an extended L-band broadband amplifier

    Recently, Hu Lili, a research group of the Advanced Laser and Optoelectronic Functional Materials Department of the Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, proposed a new scheme based on field strength optimization of Er doped silicate fiber as an extended L-band broadband amplifier. Relevant research achievements were published in Optics Letters under the tit...

    2024-06-05
    Xem bản dịch
  • Multinational research team achieves breakthrough in diamond Raman laser oscillator

    Recently, the team led by Professor Lv Zhiwei and Professor Bai Zhenxu from Hebei University of Technology, in collaboration with Professor Richard Mildren from Macquarie University in Australia and Professor Takashige Omatsu from Chiba University in Japan, successfully achieved direct output of Raman vortex optical rotation with large wavelength extension in a diamond Raman laser oscillator. This...

    02-27
    Xem bản dịch