Saturday, July 26, 2025
LBNN
  • Business
  • Markets
  • Politics
  • Crypto
  • Finance
  • Energy
  • Technology
  • Taxes
  • Creator Economy
  • Wealth Management
  • Documentaries
No Result
View All Result
LBNN

New neural framework enhances reconstruction of high-resolution images

Simon Osuji by Simon Osuji
September 6, 2024
in Artificial Intelligence
0
New neural framework enhances reconstruction of high-resolution images
0
SHARES
1
VIEWS
Share on FacebookShare on Twitter


New neural framework enhances reconstruction of high-resolution images
Neural phase retrieval (NeuPh) employs a CNN-based encoder to learn measurement-specific information and encode them into a latent-space representation. The MLP decoder reconstructs the phase values at specific locations with an increased spatial resolution by synthesizing local conditional information from the corresponding latent vectors. Credit: H. Wang et al., doi 10.1117/1.APN.3.5.056005.

Deep learning (DL) has significantly transformed the field of computational imaging, offering powerful solutions to enhance performance and address a variety of challenges. Traditional methods often rely on discrete pixel representations, which limit resolution and fail to capture the continuous and multiscale nature of physical objects. Recent research from Boston University (BU) presents a novel approach to overcome these limitations.

Related posts

SteelSeries Rival 3 Gen 2 Review: Good Budget Gaming Mice

SteelSeries Rival 3 Gen 2 Review: Good Budget Gaming Mice

July 26, 2025
Join Our Next Livestream: Inside Katie Drummond’s Viral Interview With Bryan Johnson

Join Our Next Livestream: Inside Katie Drummond’s Viral Interview With Bryan Johnson

July 25, 2025

As reported in Advanced Photonics Nexus, researchers from BU’s Computational Imaging Systems Lab have introduced a local conditional neural field (LCNF) network, which they use to address the problem. Their scalable and generalizable LCNF system is known as “neural phase retrieval”—”NeuPh” for short.

NeuPh leverages advanced DL techniques to reconstruct high-resolution phase information from low-resolution measurements. This method employs a convolutional neural network (CNN)-based encoder to compress captured images into a compact latent-space representation.

Then, this is followed by a multilayer perceptron (MLP)-based decoder that reconstructs high-resolution phase values, effectively capturing multiscale object information. By doing so, NeuPh provides robust resolution enhancement and outperforms both traditional physical model-based methods and current state-of-the-art neural networks.

The reported results highlight NeuPh’s ability to apply continuous and smooth object priors to the reconstruction, showcasing more accurate results compared to existing models. Using experimental datasets, the researchers demonstrated that NeuPh can accurately reconstruct intricate subcellular structures, eliminate common artifacts such as residual phase unwrapping errors, noise, and background artifacts, and maintain high accuracy even with limited or imperfect training data.

NeuPh also exhibits strong generalization capabilities. It consistently performs high-resolution reconstructions when trained with very limited data or under different experimental conditions. This adaptability is further enhanced by training on physics-model-simulated datasets, which allows NeuPh to generalize well to real experimental data.

According to lead researcher Hao Wang, “We also explored a hybrid training strategy combining both experimental and simulated datasets, emphasizing the importance of aligning the data distribution between simulations and real experiments to ensure effective network training.”

Wang adds, “NeuPh facilitates ‘super-resolution’ reconstruction, surpassing the diffraction limit of input measurements. By utilizing ‘super-resolved’ latent information during training, NeuPh achieves scalable and generalizable high-resolution image reconstruction from low-resolution intensity images, applicable to a wide range of objects with varying spatial scales and resolutions.”

As a scalable, robust, accurate, and generalizable solution for phase retrieval, NeuPh opens new possibilities for DL-based computational imaging techniques.

More information:
Hao Wang et al, NeuPh: scalable and generalizable neural phase retrieval with local conditional neural fields, Advanced Photonics Nexus (2024). DOI: 10.1117/1.APN.3.5.056005

Citation:
New neural framework enhances reconstruction of high-resolution images (2024, September 5)
retrieved 5 September 2024
from https://techxplore.com/news/2024-09-neural-framework-reconstruction-high-resolution.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Previous Post

Hon. Okello Addresses 2nd Indonesia-Africa Forum 2024 in Bali

Next Post

Changpeng Zhao Binance Exit Revealed to be a Lifetime Ban

Next Post
Changpeng Zhao Binance Exit Revealed to be a Lifetime Ban

Changpeng Zhao Binance Exit Revealed to be a Lifetime Ban

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

RECOMMENDED NEWS

xAI breaks records with ‘Colossus’ AI training system

xAI breaks records with ‘Colossus’ AI training system

11 months ago
South Africa: Africa Must Plan Its Own Energy Transition, Says Speakers At Africa Oil Week

South Africa: Africa Must Plan Its Own Energy Transition, Says Speakers At Africa Oil Week

2 years ago
Trump’s attacks on early voting muddle Republican election plans

Trump’s attacks on early voting muddle Republican election plans

1 year ago
Defections alone won’t break ISWAP terror group

Defections alone won’t break ISWAP terror group

1 year ago

POPULAR NEWS

  • Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    Ghana to build three oil refineries, five petrochemical plants in energy sector overhaul

    0 shares
    Share 0 Tweet 0
  • When Will SHIB Reach $1? Here’s What ChatGPT Says

    0 shares
    Share 0 Tweet 0
  • The world’s top 10 most valuable car brands in 2025

    0 shares
    Share 0 Tweet 0
  • Top 10 African countries with the highest GDP per capita in 2025

    0 shares
    Share 0 Tweet 0
  • Global ranking of Top 5 smartphone brands in Q3, 2024

    0 shares
    Share 0 Tweet 0
  • Privacy Policy
  • Contact

© 2023 LBNN - All rights reserved.

No Result
View All Result
  • Home
  • Business
  • Politics
  • Markets
  • Crypto
  • Economics
    • Manufacturing
    • Real Estate
    • Infrastructure
  • Finance
  • Energy
  • Creator Economy
  • Wealth Management
  • Taxes
  • Telecoms
  • Military & Defense
  • Careers
  • Technology
  • Artificial Intelligence
  • Investigative journalism
  • Art & Culture
  • Documentaries
  • Quizzes
    • Enneagram quiz
  • Newsletters
    • LBNN Newsletter
    • Divergent Capitalist

© 2023 LBNN - All rights reserved.