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

Vision01:24

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
Depth Perception and Spatial Vision01:15

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

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection.

Proceedings. IEEE International Conference on Computer Vision·2026
Same author

Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data.

Machine intelligence research (Beijing)·2026
Same author

Proximity-Driven Protein Ligation Beyond the Concentration Limit.

Journal of the American Chemical Society·2026
Same author

Proactive Health: A Culture-Centered Study on the Differential Health Practices of Older Adults in Elderly Care Institutions in China.

Health communication·2026
Same author

Direct Photoredox Synthesis of <i>N</i>-Linked Glycoproteins.

Journal of the American Chemical Society·2026
Same author

Elemental phosphorus-stabilized Ni<sub>2</sub>P for efficient electrooxidation of 5-hydroxymethylfurfural to 2,5-furandicarboxylic acid.

Chemical communications (Cambridge, England)·2026

Related Experiment Video

Updated: Jul 15, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding.

Wufei Ma1, Guofeng Zhang1, Qihao Liu1

  • 1Johns Hopkins University.

Advances in Neural Information Processing Systems
|July 14, 2026
PubMed
Summary

This study introduces ImageNet3D, a large dataset for general-purpose 3D understanding in computer vision. It enables the development of models that can infer both 2D and 3D information for diverse objects.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 15, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

Area of Science:

  • Computer Vision
  • Machine Learning
  • 3D Computer Vision

Background:

  • General-purpose 3D understanding requires inferring 2D and 3D information for arbitrary rigid objects.
  • Existing datasets lack sufficient categories and annotation quality, hindering model generalization.
  • Current models often specialize in specific categories, failing to generalize to unseen objects.

Purpose of the Study:

  • Introduce ImageNet3D, a large-scale dataset for general-purpose object-level 3D understanding.
  • Enable analysis of 3D awareness in visual foundation models.
  • Facilitate the development of models for inferring 2D/3D information and integrating with large language models for 3D reasoning.

Main Methods:

  • Augmented 200 ImageNet categories with 2D bounding boxes, 3D pose, and 3D location annotations.
  • Included image captions with interleaved 3D information.
  • Introduced new tasks: probing object-level 3D awareness and open-vocabulary pose estimation.

Main Results:

  • The ImageNet3D dataset supports analysis and development of general-purpose 3D understanding models.
  • Experimental results demonstrate the dataset's potential for improving vision models' 3D perception.
  • The dataset facilitates research into unified 3D models and large language model integration.

Conclusions:

  • ImageNet3D advances research in general-purpose object-level 3D understanding.
  • The dataset enables the creation of more robust and generalizable computer vision models.
  • Future work can leverage ImageNet3D for enhanced 3D reasoning capabilities in AI.