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

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026

Same author

Survival and prognostic factors of parotid malignancies in Northern Italy: a multicentric study.

Acta otorhinolaryngologica Italica : organo ufficiale della Societa italiana di otorinolaringologia e chirurgia cervico-facciale·2026

Same author

Optimizing deep learning models for on-orbit deployment through neural architecture search.

Scientific reports·2025

Same author

Assessment of physical phantoms produced in the PHENOMENO project utilizing three fused filament fabrication approaches.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2025

Same author

Post-treatment head and neck cancer rehabilitation in an acute palliative care unit.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2025

Same author

Influence of parotidectomy extent on complications after benign parotid surgery.

Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery·2025

Search research articles

Related Experiment Video

Updated: Sep 16, 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

Efficient attention vision transformers for monocular depth estimation on resource-limited hardware.

Claudio Schiavella¹, Lorenzo Cirillo², Lorenzo Papa^2,3

¹Department of Computer, Control and Management Engineering (DIAG), Sapienza University of Rome, Rome, 00185, Italy. schiavella@diag.uniroma1.it.

Scientific Reports

|July 4, 2025

Summary

This study optimizes Vision Transformers for Monocular Depth Estimation by reducing computational costs. Efficient attention modules improve inference speed without sacrificing accuracy, benefiting onboard applications.

Keywords:

Computer vision Edge devices Efficient vision transformer Monocular depth estimation

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

Related Experiment Videos

Last Updated: Sep 16, 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

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

Area of Science:

Computer Vision
Deep Learning
Artificial Intelligence

Background:

Vision Transformers achieve state-of-the-art results in complex tasks like Monocular Depth Estimation.
The attention mechanism in transformers presents a quadratic computational cost, leading to slow inference, especially in resource-constrained environments.

Purpose of the Study:

To reduce the computational cost of Vision Transformer networks for Monocular Depth Estimation.
To achieve an optimal balance between estimation quality and inference speed.
To evaluate network optimization strategies for improved efficiency in onboard applications.

Main Methods:

Leveraging efficient attention modules to decrease computational complexity.
Applying optimization to the entire network, as well as independently to the encoder and decoder.
Utilizing Pareto Frontier analysis to identify the optimal trade-off between quality and inference time.

Main Results:

Optimized networks demonstrate performance comparable to or exceeding baseline models.
Significant improvements in inference speed were achieved across various optimized architectures.
The study successfully identified effective strategies for enhancing efficiency in Monocular Depth Estimation.

Conclusions:

Efficient attention mechanisms are crucial for accelerating Vision Transformer-based Monocular Depth Estimation.
Network optimization, including targeted encoder/decoder adjustments, enhances performance-speed trade-offs.
This research provides a pathway for deploying advanced deep learning models in real-time, edge-based applications.