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

Editorial: Synergizing large language models and computational intelligence for advanced robotic systems.

Frontiers in robotics and AI·2026

Same author

Classification of 24-h movement behaviour patterns among university students and their relationship with physical fitness: a latent profile analysis.

BMC public health·2026

Same author

SAMS-Net: A Smoothness-Anchored Monotone Neural Differential Equation Network for Failure-Only-Supervised Structural Health Indicator Construction.

Sensors (Basel, Switzerland)·2026

Same author

EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

IEEE transactions on medical imaging·2026

Same author

Ligand-mediated suppression of Ostwald ripening enables low-temperature sol-gel ZnO for efficient inverted flexible organic photovoltaics.

Nature communications·2026

Same author

Associations of 24-h movement behavior with mental health in adolescent athletes: a compositional isotemporal substitution analysis.

Frontiers in public health·2026

Same journal

Multimodal Cross-Attention Fusion of B-Mode Ultrasound and Strain Elastography for Tumor Segmentation in Robotics-Assisted Surgery.

IEEE transactions on medical robotics and bionics·2026

Same journal

A Pneumatically Actuated Robotic Assistant for MRI-Guided Stereotactic Neurosurgery.

IEEE transactions on medical robotics and bionics·2026

Same journal

Interdisciplinary Dialogues on Surgical Data Science: Revising Its Benefits for Surgical Stakeholders and Patients.

IEEE transactions on medical robotics and bionics·2026

Same journal

Concentric Tube Robot-Assisted Intracerebral Hemorrhage Evacuation: Validation in an Ovine Model.

IEEE transactions on medical robotics and bionics·2026

Same journal

Autonomous Slip-Prevention Grip Force Control and Its Potential in Shared Control of Robotic Prosthetic Hands.

IEEE transactions on medical robotics and bionics·2026

Same journal

Modeling and Control For Minimally Invasive Intracerebral Hemorrhage Evacuation.

IEEE transactions on medical robotics and bionics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 27, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Self-supervised Monocular Depth Estimation with 3D Displacement Module for Laparoscopic Images.

Chi Xu¹, Baoru Huang¹, Daniel S Elson¹

¹The Hamlyn Centre for Robotic Surgery, Department of Surgery and Cancer, Imperial College London, London SW7 2AZ, UK.

IEEE Transactions on Medical Robotics and Bionics

|September 23, 2022

Summary

This summary is machine-generated.

This study introduces a new self-supervised learning framework for accurate depth map estimation from single laparoscopic images using a 3D displacement module. The method effectively handles dynamic surgical scenes, outperforming existing models.

Keywords:

3D displacement CNN Deep learning monocular depth estimation self-supervised learning

More Related Videos

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

Related Experiment Videos

Last Updated: Aug 27, 2025

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Three-dimensional Location Approach with Silk Thread Guided Laparoscopic Segmentectomy for Liver Tumor

Published on: May 23, 2025

Area of Science:

Computer Vision
Medical Imaging
Machine Learning

Background:

Monocular depth estimation models typically assume static scenes, which is often not true in surgery.
Laparoscopic surgery presents unique challenges due to stationary cameras and dynamic instruments/tissues.

Purpose of the Study:

To develop a novel self-supervised training framework for accurate per-pixel depth map estimation from single laparoscopic images.
To address the limitations of existing models in dynamic surgical environments.

Main Methods:

Proposed a 3D displacement (3DD) module to establish frame relationships instead of relying on ego-motion estimation.
Utilized a convolutional neural network (CNN) within the 3DD module to predict 3D point cloud displacement between frames.
Introduced a depth consistency module to effectively constrain 3D displacement by maintaining consistency between updated and estimated depths.

Main Results:

The proposed method achieved remarkable performance in monocular depth estimation on the Hamlyn surgical dataset.
The framework successfully generated ground truth depth maps.
Outperformed established models such as monodepth, monodepth2, and packnet.

Conclusions:

The novel self-supervised training framework with a 3DD module offers a robust solution for depth estimation in laparoscopic surgery.
The depth consistency module effectively constrains 3D displacement, improving accuracy in dynamic surgical scenes.
This approach advances the capabilities of computer vision in medical applications.