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 Concept Videos

Continuous -time Fourier Transform01:11

Continuous -time Fourier Transform

1.3K
The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...
1.3K
Properties of Fourier Transform I01:21

Properties of Fourier Transform I

886
The application of Fourier Transform properties in radio broadcasting is multifaceted, enabling significant advancements in the way signals are transmitted and received. Key areas where these properties are utilized include simultaneous multi-channel transmission, audio clip speed adjustments, live broadcast delays for different time zones, audio frequency adjustments, and signal demodulation.
In radio broadcasting, multiple audio signals often need to be transmitted simultaneously. The Fourier...
886
Properties of Fourier Transform II01:24

Properties of Fourier Transform II

1.0K
The Fourier Transform (FT) is an essential mathematical tool in signal processing, transforming a time-domain signal into its frequency-domain representation. This transformation elucidates the relationship between time and frequency domains through several properties, each revealing unique aspects of signal behavior.
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
1.0K
Discrete Fourier Transform01:15

Discrete Fourier Transform

1.3K
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
1.3K
Fast Fourier Transform01:10

Fast Fourier Transform

1.3K
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
1.3K
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

2.7K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
2.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Explainable, Generative and Agentic Artificial Intelligence for the Peripheral Blood Film.

International journal of laboratory hematology·2026
Same author

An Episode Memory-Guided Dual-Stage Framework for Long-Form Video Temporal Grounding.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Single-Image Reflection Removal via Iterative Prompt Learning of Reflection Level.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

WBCAtt+: Fine-grained pixel-level morphological annotations for white blood cell images.

Medical image analysis·2026
Same author

Open-Set Anomaly Segmentation in Complex Scenarios.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

COIL-PS: continuous and online illumination planning for photometric stereo.

Optics express·2026

Related Experiment Video

Updated: Apr 30, 2026

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
11:34

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

15.6K

Revisiting One-Stage Deep Uncalibrated Photometric Stereo via Fourier Embedding.

Yakun Ju, Boxin Shi, Bihan Wen

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 2, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study presents FUPS-Net, a novel one-stage deep learning network for uncalibrated photometric stereo (UPS). It accurately reconstructs 3D shapes of non-Lambertian objects by implicitly learning lighting and geometry features using Fourier transforms, improving upon traditional two-stage methods.

    More Related Videos

    A Guide to Structured Illumination TIRF Microscopy at High Speed with Multiple Colors
    11:15

    A Guide to Structured Illumination TIRF Microscopy at High Speed with Multiple Colors

    Published on: May 30, 2016

    25.1K
    Three-dimensional Super Resolution Microscopy of F-actin Filaments by Interferometric PhotoActivated Localization Microscopy iPALM
    11:57

    Three-dimensional Super Resolution Microscopy of F-actin Filaments by Interferometric PhotoActivated Localization Microscopy iPALM

    Published on: December 1, 2016

    10.7K

    Related Experiment Videos

    Last Updated: Apr 30, 2026

    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
    11:34

    High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

    Published on: December 3, 2013

    15.6K
    A Guide to Structured Illumination TIRF Microscopy at High Speed with Multiple Colors
    11:15

    A Guide to Structured Illumination TIRF Microscopy at High Speed with Multiple Colors

    Published on: May 30, 2016

    25.1K
    Three-dimensional Super Resolution Microscopy of F-actin Filaments by Interferometric PhotoActivated Localization Microscopy iPALM
    11:57

    Three-dimensional Super Resolution Microscopy of F-actin Filaments by Interferometric PhotoActivated Localization Microscopy iPALM

    Published on: December 1, 2016

    10.7K

    Area of Science:

    • Computer Vision
    • 3D Reconstruction
    • Photometric Stereo

    Background:

    • Traditional uncalibrated photometric stereo (UPS) methods often use two-stage approaches, separating lighting estimation from surface normal prediction.
    • These two-stage networks suffer from error propagation due to disjointed training and explicit light calibration limitations.
    • The complex interplay between lighting and shading in non-Lambertian materials poses challenges for direct surface normal estimation.

    Purpose of the Study:

    • To introduce a novel one-stage deep learning network, FUPS-Net, for uncalibrated photometric stereo (UPS).
    • To overcome the limitations of existing two-stage UPS methods, including error propagation and disjointed training.
    • To achieve accurate 3D surface reconstruction for non-Lambertian objects under unknown lighting conditions.

    Main Methods:

    • Developed a one-stage deep uncalibrated photometric stereo network (FUPS-Net) utilizing an embedded Fourier transform.
    • Introduced Fourier Embedding Extraction (FEE) and Fourier Embedding Aggregation (FEA) blocks to decompose and learn lighting and geometry features in the Fourier domain.
    • Proposed a Frequency-Spatial Weighted (FSW) block to integrate frequency and spatial domain features for enhanced surface reconstruction.

    Main Results:

    • FUPS-Net demonstrates superior performance in 3D surface reconstruction compared to existing two-stage UPS methods on synthetic and real datasets.
    • The one-stage approach offers improved training stability and a more concise end-to-end structure.
    • The method effectively resolves geometry-lighting ambiguity by implicitly learning features in the Fourier domain.

    Conclusions:

    • FUPS-Net presents a significant advancement in deep learning-based uncalibrated photometric stereo.
    • The Fourier domain decomposition strategy provides a robust and efficient method for handling non-Lambertian objects.
    • This work offers a promising new strategy for future research in 3D shape reconstruction using photometric stereo.