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

Pose-oblivious shape signature.

Ran Gal1, Ariel Shamir, Daniel Cohen-Or

  • 1Schol of Computer Science, Tel-Aviv University, Israel. galran2@gmail.com

IEEE Transactions on Visualization and Computer Graphics
|January 16, 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

Gait-Synced Translation Gain for Naturalistic VR Motion.

IEEE transactions on visualization and computer graphics·2026
Same author

Latent representation of H&E images retains biological information in a breast cancer cohort.

PloS one·2025
Same author

One Shot Learning for Edge Detection on Point Clouds.

IEEE transactions on visualization and computer graphics·2025
Same author

Sticky Links: Encoding Quantitative Data of Graph Edges.

IEEE transactions on visualization and computer graphics·2024
Same author

Using deep neural networks to disentangle visual and semantic information in human perception and memory.

Nature human behaviour·2024
Same author

DO-Conv: Depthwise Over-Parameterized Convolutional Layer.

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

Multi-Perception Crowd: Learning to combine entity and implicit perception for diverse crowd simulation.

IEEE transactions on visualization and computer graphics·2026
Same journal

Hiding in Plain Sight: Camouflaging Real-world Objects.

IEEE transactions on visualization and computer graphics·2026
Same journal

RTF2Mesh: Restricted Tangent Face Based Mesh Compression With Neural Displacement Fields.

IEEE transactions on visualization and computer graphics·2026
Same journal

Practical Occluder Generation for Mobile Games.

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

We introduce a novel pose-oblivious 3D shape signature for efficient 3D shape retrieval. This signature is insensitive to pose changes and topology variations, enabling robust shape matching.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Geometric Modeling

Background:

  • 3D shape signatures are crucial for efficient shape retrieval, typically capturing scale, translation, and rotation invariance.
  • Existing methods often struggle with pose variations and topological changes in 3D shapes.

Purpose of the Study:

  • To introduce a novel 3D shape signature that is pose-oblivious, meaning it is invariant to skeletal articulations and other pose transformations.
  • To develop a signature that is also insensitive to topological changes, allowing matching of shapes with different genus.
  • To retain the simplicity and speed of traditional signature indexing methods.

Main Methods:

  • The proposed shape signature is a 2D histogram combining distributions of two scalar functions defined on the 3D shape's boundary.

Related Experiment Videos

  • The first function is the novel 'local-diameter function,' measuring the diameter of the shape's neighborhood for each vertex.
  • The second function is the 'centricity function,' calculating the average geodesic distance from each vertex to all others on the mesh.

    • Main Results:

    • The local-diameter function provides an informative, pose-insensitive measure of shape.
    • The 2D histogram effectively captures global geometric properties, robust to pose and topological variations.
    • Evaluation demonstrated the signature's effectiveness in a 3D search engine across diverse model databases.

    Conclusions:

    • The developed pose-oblivious shape signature offers a significant advancement in 3D shape retrieval.
    • Its insensitivity to pose and topology enables more robust and versatile shape matching compared to existing methods.
    • The signature's efficiency and simplicity make it suitable for large-scale 3D search engine applications.