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

Variational surface interpolation from sparse point and normal data.

Jan Erik Solem1, Henrik Aanaes, Anders Heyden

  • 1School of Technology and Society, Malmö University, SE-205 06 Malmö, Sweden. jes@ts.mah.se

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 17, 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

Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings.

Medical physics·2025
Same author

Longitudinal outcome prediction of prostate cancer patients on active surveillance using multiple instance learning.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Breast cancer classification in point-of-care ultrasound imaging-the impact of training data.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Digitizing the Appearance of 3D Printing Materials Using a Spectrophotometer.

Sensors (Basel, Switzerland)·2024
Same author

Artificial intelligence for detection of prostate cancer in biopsies during active surveillance.

BJU international·2024
Same author

Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer's disease in patients with mild cognitive symptoms.

Alzheimer's research & therapy·2024

This study introduces a novel variational framework for surface reconstruction using sparse visual cues like specularities. The method effectively reconstructs surfaces even with limited data, advancing computer vision techniques.

Area of Science:

  • Computer Vision
  • Computational Geometry
  • Image Processing

Background:

  • Traditional surface reconstruction often relies on dense visual cues.
  • Sparse cues like specularities and silhouettes are frequently the only available information.
  • Integrating sparse cues into existing frameworks remains a challenge.

Purpose of the Study:

  • To develop a variational framework capable of utilizing sparse visual cues for surface reconstruction.
  • To enable surface reconstruction from extremely limited data.
  • To validate the approach on the challenging shape-from-specularities problem.

Main Methods:

  • Formulation of sparse variational constraints within a level set framework.
  • Enforcement of constraints on surface points and surface normals.

Related Experiment Videos

  • Application of the method to sparse data scenarios.

    • Main Results:

    • Demonstrated capability to reconstruct surfaces from sparse data.
    • Successful application and validation on the shape-from-specularities problem.
    • The framework can be used alone or with dense constraints.

    Conclusions:

    • The proposed sparse variational constraints effectively handle limited visual information for surface reconstruction.
    • This approach expands the applicability of surface reconstruction techniques to scenarios with sparse data.
    • The method offers a robust solution for problems like shape-from-specularities.