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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

1.5K
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.
1.5K
Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

339
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
339
Neural Circuits01:25

Neural Circuits

2.4K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.4K
Influence of Earth's Curvature and Atmospheric Refraction on Leveling01:26

Influence of Earth's Curvature and Atmospheric Refraction on Leveling

654
During leveling, the Earth's curvature and atmospheric refraction introduce deviations in the line of sight from a true horizontal reference. When the line of sight is leveled, it remains perpendicular to the plumb line only at a single point. Beyond this, it deviates due to the Earth’s curvature, represented by the correction C. For a sight distance D, the deviation can be derived using the relationship:This relationship shows that the deviation increases quadratically with distance. Over a...
654
Curvilinear Motion: Normal and Tangential Components01:27

Curvilinear Motion: Normal and Tangential Components

693
When a car traverses a curved road, its motion can be elucidated by breaking it down into tangential and normal components. The car-centric coordinates attached to the vehicle move with it.
The positive direction of the t-axis aligns with the increasing position of the car along the curved path, denoted by the unit vector ut. Simultaneously, the n-axis, perpendicular to the t-axis, dissects the curved path into differential arc segments, each forming the arc of a circle with a radius of...
693
Uniform Depth Channel Flow01:27

Uniform Depth Channel Flow

427
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
427

You might also read

Related Articles

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

Sort by
Same author

Cohort profile: Sheyang Mini Birth Cohort Study (SMBCS).

BMJ open·2026
Same author

Occurrence, Bioaccumulation and Dietary Exposure Assessment of Legacy and Emerging Per- and Polyfluoroalkyl Substances (PFAS) in Freshwater Fish from Zhejiang Markets: Implications for Human Health Risks.

Toxics·2026
Same author

Generalized Kullback-Leibler Divergence Loss.

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

Efficient and accurate neural-field reconstruction using resistive memory.

Nature·2026
Same author

S $^{2}$ VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix.

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

Resistive memory-based neural differential equation solver for score-based diffusion model.

Nature communications·2026

Related Experiment Video

Updated: Dec 10, 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

876

GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal

Xiaojuan Qi, Zhengzhe Liu, Renjie Liao

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 2, 2020
    PubMed
    Summary

    This study introduces GeoNet++, a geometric neural network for predicting depth and surface normals from single images. It enhances 3D reconstruction quality and introduces a new metric, 3DGM, for evaluating depth prediction accuracy.

    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

    678

    Related Experiment Videos

    Last Updated: Dec 10, 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

    876
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    678

    Area of Science:

    • Computer Vision
    • Machine Learning
    • 3D Geometry

    Background:

    • Accurate depth and surface normal estimation from single images is crucial for 3D scene understanding.
    • Existing methods often struggle with boundary details and 3D consistency.

    Purpose of the Study:

    • To propose GeoNet++, a novel geometric neural network for joint depth and surface normal prediction.
    • To introduce a new 3D geometric metric (3DGM) for evaluating depth prediction quality.
    • To improve 3D reconstruction accuracy and pixel-wise precision.

    Main Methods:

    • Developed GeoNet++, a two-stream Convolutional Neural Network (CNN) with depth-to-normal and normal-to-depth modules.
    • Incorporated an edge-aware refinement module to exploit boundary information.
    • Proposed the 3D Geometric Metric (3DGM) focusing on 3D surface normal reconstruction quality.

    Main Results:

    • GeoNet++ effectively predicts depth and surface normals with high 3D consistency and sharp boundaries.
    • The proposed 3DGM metric provides a more natural evaluation for 3D applications compared to pixel-wise metrics.
    • Experiments on NYUD-V2 and KITTI datasets demonstrate superior performance in boundary detail and 3D surface reconstruction.

    Conclusions:

    • GeoNet++ offers a robust framework for enhancing depth and surface normal prediction, leading to improved 3D scene reconstruction.
    • The generic nature of GeoNet++ allows its integration into existing frameworks to boost performance.
    • The 3DGM metric offers a valuable new tool for assessing depth prediction quality in 3D contexts.