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

Neural-network-Based adaptive hybrid-reflectance model for 3-D surface reconstruction.

Chin-Teng Lin1, Wen-Chang Cheng, Sheng-Fu Liang

  • 1Department of Electrical and Control Engineering, National Chiao-Tung University, Hsinchu, Taiwan. ctlin@mail.nctu.edu.tw

IEEE Transactions on Neural Networks
|December 14, 2005
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

Clinical Applications of Deep Learning for Glottal Area Segmentation and Glottal Area Waveform Feature Computation.

IEEE open journal of engineering in medicine and biology·2026
Same author

Neural Spelling: A Spell-Based BCI System for Language Neural Decoding.

IEEE transactions on bio-medical engineering·2026
Same author

A Hybrid Covert Attention-Augmented Motor Imagery Paradigm for Brain-Computer Interfaces.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Distinct effects of empathy on self-other processing revealed by different behavioral and EEG indices.

Cognitive, affective & behavioral neuroscience·2026
Same author

Biologically-constrained spiking neural network for neuromodulation in locomotor recovery after spinal cord injury.

PLoS computational biology·2026
Same author

Effects of inflammatory markers and sleep quality in stroke patients by reducing residential PM<sub>2.5</sub> levels: A case-crossover intervention study.

The Science of the total environment·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a new neural network model for 3D surface reconstruction. It accurately reconstructs surfaces by adaptively combining light reflection properties, improving accuracy for various objects.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Machine Learning

Background:

  • Traditional 3D surface reconstruction methods struggle with complex reflectance properties.
  • Accurate surface reconstruction requires handling both diffuse and specular light components.
  • Existing models often fail to account for varying surface characteristics and albedo.

Purpose of the Study:

  • To develop a novel neural-network-based adaptive hybrid-reflectance model for 3D surface reconstruction.
  • To automatically combine diffuse and specular reflectance components for improved accuracy.
  • To reconstruct 3D surfaces without prior knowledge of illuminant direction.

Main Methods:

  • A neural network model was designed to process 2D image pixel values.
  • The model adaptively combines diffuse and specular reflectance components.

Related Experiment Videos

  • Supervised learning was used to obtain surface normal vectors from the neural network output.
  • Integrability constraints were applied using the obtained normal vectors for 3D reconstruction.

    • Main Results:

    • The proposed model successfully reconstructs 3D surfaces from 2D images.
    • It accurately handles varying albedo and point characteristics, preventing surface distortion.
    • The model performs 3D surface reconstruction effectively for both facial and general objects.
    • Experimental results show superior performance compared to existing 3D reconstruction approaches.

    Conclusions:

    • The neural-network-based adaptive hybrid-reflectance model offers a robust solution for 3D surface reconstruction.
    • This approach enhances accuracy by adaptively modeling complex surface reflectance.
    • The method is generalizable to various objects, demonstrating its practical applicability.