Jove
Visualize
Contact Us

Related Experiment Videos

Image registration for image-based rendering.

Angus M K Siu1, Rynson W H Lau

  • 1Department of Computer Science, City University of Hong Kong, Hong Kong, SAR. angus@cs.cityu.edu.hk

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 11, 2005
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

An adaptive AI-based virtual reality sports system for adolescents with excess body weight: a randomized controlled trial.

Nature medicine·2025
Same author

A Contrastive-Learning Framework for Unsupervised Salient Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

GhostingNet: A Novel Approach for Glass Surface Detection With Ghosting Cues.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Structure-Informed Shadow Removal Networks.

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

Rain Removal From Light Field Images With 4D Convolution and Multi-Scale Gaussian Process.

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

Weakly-Supervised Salient Object Detection on Light Fields.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
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
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

This study introduces a novel image registration technique for image-based rendering (IBR). The method reduces required reference images by supporting a large search range, lowering costs and improving scalability.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Geometric Modeling

Background:

  • Image-based rendering (IBR) synthesizes realistic novel views but often requires numerous reference images, increasing costs.
  • Existing IBR methods struggle with translational motion, necessitating either large datasets or prior geometric information.
  • Current image registration techniques for IBR have limited search ranges and require densely sampled images, hindering scalability.

Purpose of the Study:

  • To develop an image registration technique that recovers the geometric proxy for IBR.
  • To significantly reduce the number of reference images required for IBR.
  • To enable practical IBR in scalable walkthrough environments.

Main Methods:

  • Analyzed the roles and requirements of image registration for reducing spatial sampling rates in IBR.

Related Experiment Videos

  • Presented a novel image registration technique to automatically recover geometric proxies from reference images.
  • Developed a method with a large search range to identify correspondences in sparsely sampled reference images.

    • Main Results:

    • The novel image registration technique accurately identifies correspondences even with sparse reference images.
    • Successfully recovers the geometric proxy required for image-based rendering.
    • Demonstrated the ability to support large search ranges, overcoming limitations of existing methods.

    Conclusions:

    • The developed image registration technique effectively reduces the number of reference images needed for IBR.
    • This approach significantly lowers acquisition effort, model size, and memory costs.
    • Enables more practical and scalable applications of image-based rendering.