Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

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.

You might also read

Related Articles

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

Sort by

Same author

An Improved Robust ESKF Fusion Positioning Method with a Novel UWB-VIO Initialization.

Sensors (Basel, Switzerland)·2026

Same author

A Robust Extended Kalman Filter Algorithm Based on a Sliding Window Fractional-Order Grey Prediction Model and Its Application in MINS/GNSS.

Sensors (Basel, Switzerland)·2026

Same author

A Novel Arithmetic Optimization PDR Algorithm for Smartphones.

Sensors (Basel, Switzerland)·2025

Same author

CpG ODN Combined with Gold Nanorods Enhances Immune Activation and Its Potential Mechanism.

Journal of inflammation research·2025

Same author

UWB/MEMS IMU integrated positioning method based on NLOS angle discrimination and MAP constraints.

Scientific reports·2024

Same author

Clinical effect of external ventricular drainage under intracranial pressure monitoring in the treatment of aneurysmal subarachnoid hemorrhage patients and investigation of the mechanism of miR-146a-5p/STC1 axis in inhibiting early brain injury in aneurys.

Cellular and molecular biology (Noisy-le-Grand, France)·2024

Search research articles

Related Experiment Video

Updated: Jun 11, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Lightweight monocular depth estimation using a fusion-improved transformer.

Xin Sui¹, Song Gao², Aigong Xu¹

¹School of Geomatics, Liaoning Technical University, Fuxin, 123000, China.

Scientific Reports

|September 28, 2024

Summary

This summary is machine-generated.

This study introduces a lightweight deep learning network for accurate depth estimation. The novel architecture combines convolutional neural networks (CNNs) and Transformers for efficient local and global feature extraction, achieving high accuracy and real-time performance.

Keywords:

CNN Lightweight Monocular depth estimation Self-supervision Transformer

More Related Videos

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jun 11, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Vision
Deep Learning
Artificial Intelligence

Background:

Existing deep estimation networks often prioritize accuracy over computational efficiency.
There is a need for lightweight models that can capture both local and global image features for effective depth estimation.

Purpose of the Study:

To propose a lightweight, self-supervised network for accurate and efficient depth estimation.
To integrate Convolutional Neural Networks (CNNs) and Transformers for enhanced feature extraction.

Main Methods:

A shallow CNN with depth-separable convolution for improved receptive fields.
A Transformer with a multi-depth separable convolution head transposed attention module to reduce computational load.
A two-step gating mechanism in the feedforward network for better nonlinear representation.

Main Results:

The proposed network achieves higher estimation accuracy with fewer parameters compared to other lightweight models.
Demonstrates superior generalizability across various outdoor datasets.
Achieves a fast inference speed of 87 FPS, balancing speed and accuracy.

Conclusions:

The integrated CNN-Transformer network effectively captures local-global context for depth estimation.
The model offers a compelling solution for real-time applications requiring efficient and accurate depth estimation.