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

Counting with ease: Class-agnostic counting via one-shot detection across diverse domains.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

Multi-Floor Indoor Localization Based on Multi-Modal Sensors.

Sensors (Basel, Switzerland)·2022

Same author

A Cooperative Shared Control Scheme Based on Intention Recognition for Flexible Assembly Manufacturing.

Frontiers in neurorobotics·2022

Same author

High Accurate Environmental Sound Classification: Sub-Spectrogram Segmentation versus Temporal-Frequency Attention Mechanism.

Sensors (Basel, Switzerland)·2021

Same author

Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring.

Communications biology·2021

Same author

Multimodal feature learning and fusion on B-mode ultrasonography and sonoelastography using point-wise gated deep networks for prostate cancer diagnosis.

Biomedizinische Technik. Biomedical engineering·2019

Search research articles

Related Experiment Video

Updated: May 5, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

CLIP-Mono3D: End-to-End Open-Vocabulary Monocular 3D Object Detection via Semantic-Geometric Similarity.

Zichong Gu¹, Shiyi Mu¹, Hanqi Lyu¹

¹School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China.

Sensors (Basel, Switzerland)

|May 4, 2026

Summary

This summary is machine-generated.

This study introduces CLIP-Mono3D, a novel framework for open-vocabulary 3D object detection (OV-3DOD) using a single camera. It enables robust detection of new object categories without needing pre-defined labels or extra 2D detectors.

Keywords:

3D monocular object detection autonomous driving open-vocabulary learning

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Related Experiment Videos

Last Updated: May 5, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Area of Science:

Computer Vision
Artificial Intelligence
Robotics

Background:

Open-vocabulary 3D object detection (OV-3DOD) is essential for real-world AI perception systems.
Current monocular OV-3DOD methods face limitations with fixed categories or reliance on external 2D detectors.
Bridging the gap between vision and language is key for flexible object recognition.

Purpose of the Study:

To develop an end-to-end, one-stage transformer framework for monocular OV-3DOD.
To integrate vision-language semantics directly into the 3D detection pipeline.
To achieve robust zero-shot generalization to unseen object categories.

Main Methods:

Proposed CLIP-Mono3D, an end-to-end one-stage transformer framework.
Leveraged CLIP-derived semantic priors to guide object query grounding.
Introduced OV-KITTI, a new benchmark dataset with extended categories for OV-3DOD.
Utilized semantically salient regions for improved object localization.

Main Results:

CLIP-Mono3D demonstrated strong performance in open-vocabulary scenarios.
Achieved robust zero-shot generalization to novel object categories.
Outperformed existing methods on the OV-KITTI benchmark.
Showcased competitive results on KITTI and Argoverse datasets.

Conclusions:

CLIP-Mono3D effectively integrates vision-language models for monocular OV-3DOD.
The proposed framework offers a powerful solution for detecting objects across diverse categories.
CLIP-Mono3D advances the capabilities of real-world perception systems through enhanced generalization.