Skip to content

Latest commit

 

History

History
86 lines (54 loc) · 5 KB

README.md

File metadata and controls

86 lines (54 loc) · 5 KB
Raw

MLDM

Paper: Multi-phase FZA Lensless Imaging via Diffusion Model (MLDM)

Authors: Wenbo Wan, Huihui Ma, Zijie Mei, Huilin Zhou, Yuhao Wang, Senior Member, IEEE, Qiegen Liu, Senior Member, IEEE

Optics EXPRESS [https://opg.optica.org/oe/fulltext.cfm?uri=oe-31-12-20595&id=531211]

Date : June-2-2023
Version : 1.0
The code and the algorithm are for non-comercial use only.
Copyright 2023, School of Information Engineering, Nanchang University.

Lensless imaging shifts the burden of imaging from bulky and expensive hardware to computing, which enables new architectures for portable cameras. However, the twin image effect caused by the missing phase information in the light wave is a key factor limiting the quality of lensless imaging. Conventional single-phase encoding methods and independent reconstruction of separate channels pose challenges in removing twin images and preserving the color fidelity of the reconstructed image. In order to achieve high-quality lensless imaging, the multiphase lensless imaging via diffusion model (MLDM) is proposed. A multi-phase FZA encoder integrated on a single mask plate is used to expand the data channel of a single-shot image. The information association between the color image pixel channel and the encoded phase channel is established by extracting prior information of the data distribution based on multi-channel encoding. Finally, the reconstruction quality is improved through the use of the iterative reconstruction method. The results show that the proposed MLDM method effectively removes the influence of twin images and produces high-quality reconstructed images compared with traditional methods, and the results reconstructed using MLDM have higher structural similarity and peak signal-to-noise ratio.

The main processes of lensless imaging include optical encoding and computer decoding processes.

Reconstruction flow chart of MLDM-I algorithm.

Reconstruction flow chart of MLDM-II algorithm.

The multi-phase lensless imaging system.

Visual comparison of reconstructed images on optical experiment. (a) Ground Truth (b) BP (c) CS (d) LSGM (e) ADMM (f) MLDM-I (g) MLDM-II.

Requirements and Dependencies

python==3.7.11
Pytorch==1.7.0
tensorflow==2.4.0
torchvision==0.8.0
tensorboard==2.7.0
scipy==1.7.3
numpy==1.19.5
ninja==1.10.2
matplotlib==3.5.1
jax==0.2.26

Checkpoints

MLDM_I : We provide pretrained checkpoints. You can download pretrained models from [Baidu cloud] (https://pan.baidu.com/s/1CX7xCh1uJl-h5ZojO5SkNQ?pwd=hdtp) Extract the code (hdtp)

MLDM_II : We provide pretrained checkpoints. You can download pretrained models from [Baidu cloud] (https://pan.baidu.com/s/1-0WZnOfjQ5eiTjk1aO93PQ?pwd=taf4) Extract the code (taf4)

Dataset

The dataset used to train the model in this experiment is LSUN-bedroom and LSUN-church.

place the dataset in the train file under the church folder.

Train:

python main.py --config=configs/ve/church_ncsnpp_continuous.py --workdir=exp_train_church_max1_N1000 --mode=train --eval_folder=result

Test:

Simulate : python MLDM_reconstruction_simulate.py

Experiment : python MLDM_reconstruction_experiment.py

Acknowledgement

The implementation is based on this repository: https://github.com/yang-song/score_sde_pytorch.

Other Related Projects

  • Lens-less imaging via score-based generative model
    [Paper] [Code]

  • Imaging through scattering media via generative diffusion model
    [Paper] [Code]

  • Dual-domain Mean-reverting Diffusion Model-enhanced Temporal Compressive Coherent Diffraction Imaging
    [Paper] [Code]

  • High-resolution iterative reconstruction at extremely low sampling rate for Fourier single-pixel imaging via diffusion model
    [Paper] [Code]

  • Real-time intelligent 3D holographic photography for real-world scenarios
    [Paper] [Code]