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 Experiment Videos

3-D model-based frame interpolation for distributed video coding of static scenes.

Matthieu Maitre1, Christine Guillemot, Luce Morin

  • 1Beckman Institute, University of Illinois at UrbanaChampaign, Urbana, IL 61801, USA. maitre@uiuc.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|May 12, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Multispectral extended depth-of-field fluorescence microscopy with co-designed meta-optics and neural reconstruction.

Light, science & applications·2026
Same author

Learning flat optics for extended depth of field microscopy imaging.

Nanophotonics (Berlin, Germany)·2024
Same author

Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

PS-NET: an end-to-end phase space depth estimation approach for computer-generated holograms.

Optics express·2024
Same author

EDDMF: An Efficient Deep Discrepancy Measuring Framework for Full-Reference Light Field Image Quality Assessment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

HEADSET: Human Emotion Awareness under Partial Occlusions Multimodal DataSET.

IEEE transactions on visualization and computer graphics·2023
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align Then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study enhances video distributed coding for moving cameras by improving side information extraction. New feature tracking methods significantly boost rate-distortion performance for applications like augmented reality.

Area of Science:

  • Computer Vision
  • Video Coding
  • 3D Reconstruction

Background:

  • Distributed video coding (DVC) is crucial for applications like augmented reality and drone exploration.
  • Extracting accurate side information for DVC in 3D environments with camera motion is challenging.
  • Existing methods struggle with motion inaccuracies between key frames, limiting rate-distortion (RD) performance.

Purpose of the Study:

  • To improve side information extraction for distributed video coding in 3D environments with camera motion.
  • To leverage the structure-from-motion paradigm for enhanced DVC.
  • To overcome RD performance limitations caused by motion misalignment in Wyner-Ziv (WZ) frames.

Main Methods:

  • Developed two geometry-constrained interpolation methods: block matching along epipolar lines and 3D mesh fitting.

Related Experiment Videos

  • Utilized a robust sub-pel feature point matching algorithm for semi-dense correspondences.
  • Introduced two feature point tracking techniques to recover WZ frame camera parameters.

    • Main Results:

    • Decoder-side tracking significantly improved RD performance by correcting misalignments.
    • Encoder-side tracking further boosted RD performance and enabled adaptive key frame frequency.
    • The methods demonstrated effectiveness for video captured by a moving camera in static 3D environments.

    Conclusions:

    • Feature point tracking is vital for accurate side information in DVC of dynamic 3D scenes.
    • The proposed tracking techniques offer substantial RD performance gains.
    • Adaptive key frame selection based on motion analysis enhances coding efficiency.