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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

12.0K
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...
12.0K
Upsampling01:22

Upsampling

467
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...
467
Deconvolution01:20

Deconvolution

417
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
417

You might also read

Related Articles

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

Sort by
Same author

Selective binding of phorbol esters and diacylglycerol by individual C1 domains of the PKD family.

The Biochemical journal·2007
Same author

[Investigation and analysis of China residents' environmental conservation desire].

Ying yong sheng tai xue bao = The journal of applied ecology·2007
Same author

[Analysis and identification of sea cucumber and products].

Guang pu xue yu guang pu fen xi = Guang pu·2007
Same author

Systematic identification of C. elegans miRISC proteins, miRNAs, and mRNA targets by their interactions with GW182 proteins AIN-1 and AIN-2.

Molecular cell·2007
Same author

HDAC inhibitor PCI-24781 decreases RAD51 expression and inhibits homologous recombination.

Proceedings of the National Academy of Sciences of the United States of America·2007
Same author

[Distribution and differentiation of marrow mesenchymal cells in tumor tissue: experimental with rabbits].

Zhonghua yi xue za zhi·2007

Related Experiment Video

Updated: Nov 21, 2025

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.5K

Exploit Camera Raw Data for Video Super- Resolution via Hidden Markov Model Inference.

Xiaohong Liu, Kangdi Shi, Zhe Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 13, 2021
    PubMed
    Summary

    This study introduces a novel video super-resolution (VSR) method that directly uses camera raw data, overcoming limitations of traditional methods relying on processed video. This approach enhances image quality by leveraging richer sensor information for superior results.

    More Related Videos

    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
    11:34

    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

    Published on: December 3, 2013

    15.9K
    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

    8.7K

    Related Experiment Videos

    Last Updated: Nov 21, 2025

    Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
    10:16

    Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

    Published on: February 8, 2014

    12.5K
    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
    11:34

    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

    Published on: December 3, 2013

    15.9K
    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

    8.7K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Current deep-learning Video Super-Resolution (VSR) methods utilize processed video, leading to suboptimal results due to information loss from camera Image Signal Processor (ISP) operations.
    • VSR is typically a pre-processing step in the real imaging pipeline, yet current methods do not align with this workflow.

    Purpose of the Study:

    • To propose a new VSR method that directly processes camera sensor data (raw video) instead of ISP-processed video.
    • To introduce a Raw Video Dataset (RawVD) for training and evaluating VSR models on raw camera data.

    Main Methods:

    • A novel VSR method incorporating a Successive Deep Inference (SDI) module and a reconstruction module.
    • The SDI module uses deformable convolutions for pairwise feature fusion, inspired by Hidden Markov Model (HMM) inference principles.
    • The reconstruction module employs Attention-based Residual Dense Blocks (ARDBs) for feature refinement and color correction.

    Main Results:

    • The proposed method achieves superior Video Super-Resolution (VSR) performance compared to state-of-the-art methods.
    • The effectiveness is attributed to the use of informative camera raw data and the proposed network architecture.
    • The method demonstrates adaptability to specific camera Image Signal Processor (ISP) pipelines.

    Conclusions:

    • Directly utilizing camera raw data for VSR offers significant advantages over using ISP-processed video.
    • The proposed VSR method, leveraging raw data and a specialized architecture, provides state-of-the-art performance and flexibility.
    • The developed RawVD is crucial for advancing research in raw video super-resolution.