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

Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

303
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
303
Upsampling01:22

Upsampling

294
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...
294
Convolution Properties II01:17

Convolution Properties II

264
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
264
Convolution Properties I01:20

Convolution Properties I

218
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
218
Transformers01:26

Transformers

1.1K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.1K
Continuous -time Fourier Transform01:11

Continuous -time Fourier Transform

381
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
381

You might also read

Related Articles

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

Sort by
Same author

Dissolving microneedle patches loaded with resveratrol albumin nanoclusters for corneal anti-angiogenic therapy.

International journal of pharmaceutics: X·2026
Same author

China's path to dynamically tighten air quality standards for health.

Science bulletin·2026
Same author

Aligning Climate Mitigation, Air Pollution Control, and Healthy Aging.

Health data science·2026
Same author

Eosinophil cationic protein-driven type 2 inflammation impairs olfactory function in a murine model.

Inflammation research : official journal of the European Histamine Research Society ... [et al.]·2026
Same author

Estimating Infant and Adult Mortality Burden Attributable to Fine Particulate Matter in China from 2013 to 2023: An Environmental Justice Perspective.

Environmental science & technology·2026
Same author

Long-Term Surgical Outcomes and Influential Factors of Subthalamic Nucleus Deep Brain Stimulation for Dyskinesia in Parkinson's Disease: A 3-Year Longitudinal Cohort Study.

Clinical interventions in aging·2026

Related Experiment Video

Updated: Aug 23, 2025

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.0K

Learning a spatial-temporal texture transformer network for video inpainting.

Pengsen Ma1, Tao Xue1

  • 1School of Computer Science, Xi'an Polytechnic University, Xi'an, China.

Frontiers in Neurorobotics
|October 31, 2022
PubMed
Summary

This study introduces a new spatial-temporal texture transformer network (STTTN) for video inpainting. The STTTN effectively reconstructs damaged video frames by improving texture transfer and content recovery.

Keywords:
deep learningspatial-temporaltexture convertertransformervideo inpainting

More Related Videos

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps
11:52

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps

Published on: February 9, 2017

6.0K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Related Experiment Videos

Last Updated: Aug 23, 2025

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.0K
Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps
11:52

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps

Published on: February 9, 2017

6.0K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Video inpainting aims to restore realistic textures in damaged video frames.
  • Current methods struggle with accurate texture transfer and content reconstruction.
  • Existing approaches often neglect robust information extraction and feature correlation.

Purpose of the Study:

  • To propose a novel spatial-temporal texture transformer network (STTTN) for enhanced video inpainting.
  • To address limitations in information extraction and content reconstruction in current video inpainting models.
  • To improve the accuracy of texture transfer for damaged video frames.

Main Methods:

  • Developed a spatial-temporal texture transformer network (STTTN) with six specialized modules.
  • Modules include feature similarity, enhanced encoder, embedding, and multi-stage feature transfer (low and high frequency).
  • Employed joint feature learning across input and reference frames for comprehensive texture restoration.

Main Results:

  • The STTTN demonstrated superior performance in qualitative and quantitative experiments.
  • The model effectively reconstructs textures and content, outperforming existing methods.
  • Experiments were conducted using both stationary and moving object masks on multiple datasets.

Conclusions:

  • The proposed STTTN is an effective and reliable model for video inpainting.
  • The network's architecture facilitates accurate texture transfer and content reconstruction.
  • The STTTN advances the state-of-the-art in realistic video frame restoration.