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

A shape-from-shading method of polyhedral objects using prior information.

Hisashi Shimodaira1

  • 1Department of Information and Communications, Bunkyo University, 1100 Namegaya, Chigasaki City, Kanagawa 253-8550, Japan. shimo-hi@hi-ho.ne.jp

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 29, 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 journal

NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks.

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

A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control.

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

Robust 3D Semantic Occupancy Prediction With Calibration-Free Spatial Transformation.

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

Image Restoration via Multi-domain Learning.

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

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

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

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026

This study introduces a novel 3D shape recovery method for polyhedral objects using shading and prior information from a single 2D image. The approach effectively handles imperfect line drawings, enabling accurate shape reconstruction.

Area of Science:

  • Computer Vision
  • Computational Geometry
  • 3D Reconstruction

Background:

  • Recovering 3D polyhedral object shape from 2D images is challenging, especially with imperfect line drawings.
  • Traditional shape-from-shading methods struggle with inaccuracies in input data.

Purpose of the Study:

  • To develop a robust method for 3D shape recovery of polyhedral objects from single 2D images.
  • To address limitations of existing methods when dealing with imprecise line drawings and shading information.

Main Methods:

  • A flexible face positioning method is proposed to tolerate vertex-position errors from incorrect line drawings.
  • Prior information (horizontality, verticality, convexity/concavity) is incorporated as physical constraints.
  • Shape-from-shading is formulated as a constrained nonlinear minimization problem solved via global optimization.

Related Experiment Videos

Main Results:

  • The method successfully recovered shapes similar to actual objects from both synthetic and real-world images.
  • Experimental results demonstrate the effectiveness of the proposed approach for simple-shaped polyhedral objects.

Conclusions:

  • The developed method offers a robust solution for 3D shape recovery from single 2D images, even with noisy input.
  • Incorporating prior knowledge and flexible error handling significantly improves shape reconstruction accuracy.