Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Upsampling01:22

Upsampling

583
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
583
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

12.2K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
12.2K
Downsampling01:20

Downsampling

609
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
609

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Trimethylamine N-Oxide and Impaired Spermatogenesis in the Gut-Testis Axis: A Focused Review of Current Evidence.

Biology·2026
Same author

Regulating KO<sub>2</sub> deposition <i>via</i> crystal-void size matching in K-O<sub>2</sub> batteries.

Chemical communications (Cambridge, England)·2026
Same author

Dietary supplementation with selenium yeast during early pregnancy enhances litter size in association with antioxidant capacity, progesterone synthesis, and gut microbiota in sows.

Microbiology spectrum·2026
Same author

Insights into programmed cell death from multiple imaging modalities.

Journal of translational medicine·2026
Same author

Brain Aging in Specific Phobia: An ENIGMA-Anxiety Mega-Analysis.

Human brain mapping·2026
Same author

JA differentially regulates a SmWLIM1/MYB62-SUS1 module to control male fertility via starch biosynthesis.

Plant physiology·2026

Related Experiment Video

Updated: Jan 17, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

735

Thangka super-resolution diffusion model based on discrete cosine transform domain padding upsampling and

Xin Chen1, Liqi Ji1, Zhen Wang1

  • 1Key Laboratory of Linguistic and Cultural Computing, Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China.

Plos One
|September 25, 2025
PubMed
Summary

A new Frequency-Domain Enhanced Diffusion Super-Resolution (FDEDiff) method improves Thangka image restoration by focusing on high-frequency details and using DCT upsampling. This digital preservation technique enhances visual perception for cultural heritage applications.

More Related Videos

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.8K

Related Experiment Videos

Last Updated: Jan 17, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

735
Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.8K

Area of Science:

  • Computer Vision
  • Digital Image Processing
  • Cultural Heritage Preservation

Background:

  • Thangka traditional Tibetan paintings possess significant cultural value and unique artistic styles.
  • Existing image super-resolution methods struggle with the large size and intricate details of Thangka images, leading to poor texture restoration and perceptual quality.
  • Digital preservation and restoration are crucial for maintaining the integrity of cultural heritage like Thangka art.

Purpose of the Study:

  • To address the limitations of current super-resolution techniques for Thangka images.
  • To enhance the reconstruction of high-frequency details and intricate textures in degraded Thangka images.
  • To improve the perceptual quality of super-resolved Thangka images for cultural preservation.

Main Methods:

  • Proposed a Frequency-Domain Enhanced Diffusion Super-Resolution (FDEDiff) method.
  • Introduced a High-Frequency Focused Cross Attention Mechanism (HFC-Attention) to guide diffusion models with high-frequency features.
  • Implemented DCT Domain Padding Upsampling (DCT-Upsampling) for improved reconstruction of dense line areas using global information.
  • Constructed a novel Thangka image super-resolution dataset with 82,688 image pairs.

Main Results:

  • FDEDiff achieved state-of-the-art performance on the Thangka dataset.
  • The method attained a LPIPS score of 0.0815, indicating superior perceptual quality.
  • Demonstrated a 20% improvement in perceptual quality compared to baseline methods.
  • Successfully reconstructed high-frequency details and intricate textures, enhancing visual authenticity.

Conclusions:

  • FDEDiff effectively overcomes the challenges of super-resolving Thangka images, particularly in detail and texture reconstruction.
  • The proposed method significantly improves perceptual quality, making it suitable for cultural heritage preservation.
  • While FDEDiff has a longer inference time, the enhanced artistic authenticity justifies its use in critical cultural applications.