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

Implicit meshes for surface reconstruction.

Slobodan Ilic1, Pascal Fua

  • 1Ecole Polytechnique Fédérale de Lausanne (EPFL), Computer Vision Laboratory, CH-1015 Lausanne, Switzerland. slobodan.ilic@epfl.ch

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 14, 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

Neural illumination calibration for surgical workflow-optimized spectral imaging.

International journal of computer assisted radiology and surgery·2025
Same author

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT.

Communications medicine·2025
Same author

<i>MedShapeNet</i> - a large-scale dataset of 3D medical shapes for computer vision.

Biomedizinische Technik. Biomedical engineering·2024
Same author

Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields.

Medical image analysis·2024
Same author

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets.

Nature methods·2024
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a novel method to convert arbitrary 3D triangulated meshes into implicit surfaces. This approach combines the benefits of explicit and implicit representations for improved 3D model fitting and deformation.

Area of Science:

  • Computer Graphics
  • 3D Modeling
  • Geometric Processing

Background:

  • Explicit surfaces (e.g., triangulated meshes) are easy to deform and render but difficult to fit due to non-differentiable distance functions.
  • Implicit surfaces offer differentiable fitting but pose challenges in deformation and rendering.
  • Existing methods struggle to balance the advantages of both explicit and implicit surface representations.

Purpose of the Study:

  • To develop a hybrid method that leverages the strengths of both explicit and implicit 3D surface representations.
  • To enable the conversion of arbitrary triangulated meshes into deformable implicit surfaces.
  • To facilitate both automated fitting using implicit surface properties and intuitive user-driven deformation.

Main Methods:

Related Experiment Videos

  • A novel technique is proposed to transform arbitrary triangulated meshes into implicit surfaces.
  • The generated implicit surfaces closely approximate the original mesh geometry.
  • The method allows the implicit surface to deform in tandem with the original mesh.

    • Main Results:

    • The technique successfully converts complex, arbitrary triangulated meshes into functional implicit surfaces.
    • The resulting implicit surfaces retain the topology and shape of the original meshes.
    • Demonstrated applicability in modeling the human upper-body (face, neck, shoulders, ears) from noisy data.

    Conclusions:

    • The proposed method effectively bridges the gap between explicit and implicit 3D surface representations.
    • It enhances automated fitting algorithms by utilizing differentiable properties of implicit surfaces.
    • It supports user-friendly interaction and animation through standard deformation tools applied to the mesh.