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

Multiview photometric stereo.

Carlos Hernández Esteban1, George Vogiatzis, Roberto Cipolla

  • 1Computer Vision Group, Toshiba Research Europe, Cambridge, UK. carlos.hernandez@crl.toshiba.co.uk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 16, 2008
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

Prediction of total and regional body composition from 3D body shape.

NPJ digital medicine·2024
Same author

HexNet: An Orientation-Aware Deep Learning Framework for Omni-Directional Input.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Combined Treatment With Exenatide and Cyclosporine A or Parstatin 1-26 Results in Enhanced Reduction of Infarct Size in a Rabbit Model.

Journal of cardiovascular pharmacology·2017
Same author

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2017
Same author

Semi-supervised video segmentation using tree structured graphical models.

IEEE transactions on pattern analysis and machine intelligence·2013
Same author

Video Normals from Colored Lights.

IEEE transactions on pattern analysis and machine intelligence·2011
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 3D reconstruction algorithm for shiny, textureless objects using multiple viewpoints and varying illumination. The method accurately recovers shape and surface properties, improving upon existing techniques.

Area of Science:

  • Computer Vision
  • 3D Reconstruction
  • Photometric Stereo

Background:

  • Reconstructing textureless, shiny objects in 3D presents significant challenges for existing computer vision algorithms.
  • Traditional photometric stereo methods are often limited to single viewpoints, hindering complete surface recovery.

Purpose of the Study:

  • To develop a robust algorithm for complete and detailed 3D reconstructions of textureless shiny objects.
  • To overcome the limitations of single-viewpoint photometric stereo by incorporating multi-view and varying illumination strategies.

Main Methods:

  • Utilizes object silhouettes and images captured under changing illumination from multiple viewpoints.
  • Recovers camera motion and constructs the object's visual hull from silhouettes.
  • Employs a multi-view photometric stereo approach, initialized with recovered illumination, for closed surface reconstruction.

Related Experiment Videos

Main Results:

  • A robust technique for estimating light directions and intensities was developed.
  • A novel photometric stereo formulation combining multiple viewpoints enables closed surface reconstructions.
  • The algorithm demonstrated accurate 3D reconstructions on synthetic data and challenging real-world objects.

Conclusions:

  • The proposed algorithm successfully achieves detailed 3D reconstructions of challenging objects, including those with highly specular surfaces.
  • This multi-view photometric stereo approach significantly enhances reconstruction accuracy compared to correspondence-based multi-view stereo methods, even for textured objects.