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

Constrained texture synthesis via energy minimization.

Ganesh Ramanarayanan1, Kavita Bala

  • 1Department of Computer Science, Cornell University, Ithaca, NY 14853, USA. graman@cs.cornell.edu

IEEE Transactions on Visualization and Computer Graphics
|November 10, 2006
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

Enhancing syphilis diagnosis through innovative adaptation of wet mount microscopy.

Indian journal of dermatology, venereology and leprology·2024
Same author

Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision.

PloS one·2021
Same author

Effect of geometric sharpness on translucent material perception.

Journal of vision·2020
Same author

Scene Summarization via Motion Normalization.

IEEE transactions on visualization and computer graphics·2020
Same author

Context-Aware Asset Search for Graphic Design.

IEEE transactions on visualization and computer graphics·2018
Same author

Photometric Ambient Occlusion for Intrinsic Image Decomposition.

IEEE transactions on pattern analysis and machine intelligence·2016
Same journal

Two-phase Impulse Fluid on Particle Flow Map.

IEEE transactions on visualization and computer graphics·2026
Same journal

FGO-SLAM++: Real-time Geometry-Aware Gaussian SLAM with Continuous Opacity Field.

IEEE transactions on visualization and computer graphics·2026
Same journal

Blue Noise Dithering for Reservoir-based Spatio-temporal Importance Resampling.

IEEE transactions on visualization and computer graphics·2026
Same journal

ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

MesoSplats: Texture Synthesis with Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

IEEE transactions on visualization and computer graphics·2026
See all related articles

Constrained Minimization Synthesis (CMS) is a fast, robust algorithm for creating textures that meet specific requirements. This texture synthesis method balances constraint satisfaction and seamlessness for high-quality results.

Area of Science:

  • Computer Graphics
  • Image Processing
  • Computational Geometry

Background:

  • Texture synthesis is crucial for realistic digital content creation.
  • Existing methods may struggle with complex constraints or performance.
  • Detail synthesis requires efficient and high-fidelity techniques.

Purpose of the Study:

  • Introduce Constrained Minimization Synthesis (CMS), a novel texture synthesis algorithm.
  • Demonstrate CMS's ability to satisfy multiple constraints effectively.
  • Enhance the Image Analogies framework with superior quality and performance.

Main Methods:

  • Formulating constrained texture synthesis as an energy minimization problem.
  • Balancing constraint satisfaction and texture seamlessness metrics.

Related Experiment Videos

  • Employing graphcut energy minimization for efficient solution finding.

    • Main Results:

    • CMS provides a fast and robust approach to texture synthesis.
    • The algorithm excels at detail synthesis for low-resolution images.
    • CMS supports extended Image Analogies with improved quality and speed.

    Conclusions:

    • CMS offers a principled and efficient solution for constrained texture synthesis.
    • The algorithm's flexibility enables novel applications with combined controls.
    • CMS represents a significant advancement in texture synthesis and image manipulation.