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 Video

Updated: Dec 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

849

Deep Photometric Stereo Network with Multi-Scale Feature Aggregation.

Chanki Yu1, Sang Wook Lee1,2

  • 1Department of Media Technology, Graduate School of Media, Sogang University, Seoul 04107, Korea.

Sensors (Basel, Switzerland)
|November 6, 2020
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

Strain Field Modulation in Suspended Graphene Membranes Using Localized Electron-Beam-Induced Deposition.

ACS applied materials & interfaces·2026
Same author

Precise detection of single particles and bio-sensing applications on quartz crystal microbalance using non-linear resonance behavior.

Microsystems & nanoengineering·2026
Same author

Differential impacts of energetic reward and penalty on arm choice.

Journal of neurophysiology·2025
Same author

Development and Validation of Customizable, Adaptive SPring-Actuated Hand EXoskeleton (CASPHEX) Designed for Home-Based Training of Finger Movements Post-Stroke.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025
Same author

Dynamic Task-Related Changes in Electroencephalography Brain Connectivity During a Button-Press Task in Children with and Without Bilateral Cerebral Palsy.

Brain connectivity·2025
Same author

Detection of HPV 16 and 18 L1 genes by a nucleic acid amplification-free electrochemical biosensor powered by CRISPR/Cas9.

Bioelectrochemistry (Amsterdam, Netherlands)·2024
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a new convolutional neural network algorithm for photometric stereo, improving surface normal estimation for objects with complex surfaces and reflections. The method enhances accuracy, outperforming existing techniques, especially for uncalibrated scenarios.

Area of Science:

  • Computer Vision
  • Computer Graphics
  • Machine Learning

Background:

  • Photometric stereo traditionally estimates surface normals from images under varying illumination.
  • Non-Lambertian reflections pose challenges for traditional photometric stereo methods.
  • Accurate surface normal estimation is crucial for 3D reconstruction and material analysis.

Purpose of the Study:

  • To develop robust photometric stereo algorithms capable of handling non-Lambertian reflections.
  • To enhance surface normal estimation accuracy for objects with complex geometry and reflectance.
  • To improve both calibrated and uncalibrated photometric stereo approaches.

Main Methods:

  • A convolutional neural network (CNN) approach for surface normal estimation.
Keywords:
computer visionconvolutional neural networkdeep learningphotometric stereo

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

666
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

512

Related Experiment Videos

Last Updated: Dec 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

849
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

666
Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

512
  • Multi-scale feature aggregation using feature concatenation for improved accuracy.
  • Max pooling for an intermediate order-agnostic representation in photometric stereo.
  • Integration of the proposed scheme into existing CNN architectures.

    • Main Results:

    • Improved accuracy in both calibrated and uncalibrated photometric stereo over baseline methods.
    • The uncalibrated photometric stereo approach outperformed the state-of-the-art method.
    • Demonstrated the effectiveness of multi-scale feature aggregation for accurate surface normal estimation.
    • Validated on the DiLiGent photometric stereo benchmark dataset with ten real objects.

    Conclusions:

    • The proposed multi-scale feature aggregation scheme accurately estimates surface normals in photometric stereo.
    • The novel approach offers significant performance improvements, particularly in uncalibrated settings.
    • This work is the first to incorporate multi-scale feature aggregation in photometric stereo, advancing the field.