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.

Visual System

Visual System

Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...

Vision

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.

You might also read

Related Articles

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

Sort by

Same author

Music-selective cortex is sensitive to structure in both pitch and time.

Cerebral cortex (New York, N.Y. : 1991)·2026

Same author

Perceived authenticity drives gaze behavior when watching AI-generated videos of physical scenes.

Scientific reports·2026

Same author

Conniving With Continuations: Representing Goals in a Domain-Specific Language of Thought.

Topics in cognitive science·2026

Same author

Neural representation of action symbols in primate frontal cortex.

Nature·2026

Same author

Human-level learning of complex novel tasks as theory-based modelling, exploration and planning.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026

Same author

Reverse engineering the centered self.

Psychological review·2026

Same journal

Incipient Constituents: Phonesthemes Facilitate Word Processing in English.

Open mind : discoveries in cognitive science·2026

Same journal

Tracking Visual Statistical Learning with Steady-State Visual Evoked Potentials: Effects of Exemplar and Category Information.

Open mind : discoveries in cognitive science·2026

Same journal

Luck and Intentional Action: A Causal Account.

Open mind : discoveries in cognitive science·2026

Same journal

Expectations of Reciprocal Generosity Are Specific to Equal Relationships.

Open mind : discoveries in cognitive science·2026

Same journal

Resolving the Vagueness of Quantifiers With Explicit Expectations.

Open mind : discoveries in cognitive science·2026

Same journal

Where You Look Is What You Get: Individual Fixation Height Predicts Biases in Face Perception.

Open mind : discoveries in cognitive science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 25, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Approximating Human-Level 3D Visual Inferences With Deep Neural Networks.

Thomas P O'Connell¹, Tyler Bonnen², Yoni Friedman¹

¹Brain & Cognitive Sciences, MIT, Cambridge, MA, USA.

Open Mind : Discoveries in Cognitive Science

|February 27, 2025

Summary

This summary is machine-generated.

Deep neural networks (DNNs) struggle with 3D shape inference compared to humans. Multi-view learning objectives help DNNs, but achieving human-like 3D shape perception remains a challenge, especially for novel objects.

Keywords:

3D shape perception deep neural networks neural fields psychophysics

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: May 25, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Computer Vision
Cognitive Science
Artificial Intelligence

Background:

Humans excel at inferring 3D visual world geometry.
Deep neural networks (DNNs) often fail at 3D shape inference tasks despite human-level performance in other areas.
A gap exists in 3D shape representation between DNNs and human perception.

Purpose of the Study:

To investigate if and how the gap in 3D shape representation between DNNs and humans can be closed.
To evaluate 3D shape inference capabilities of various DNN architectures.
To identify factors influencing DNN performance in 3D shape matching tasks.

Main Methods:

Generated a stimulus set for a match-to-sample task to evaluate 3D shape inferences.
Constructed and trained 3D-aware DNNs (Light Field Network, autoencoder, convolutional) using single-view and multi-view learning objectives.
Assessed model performance against human performance on 3D shape matching and generalization to out-of-distribution categories.

Main Results:

Standard DNNs failed to reach human performance in 3D shape inference.
Multi-view DNNs approached human-level performance when training and test object categories matched.
The 3D Light Field Network showed the highest similarity to human performance, suggesting benefits of 3D inductive biases.
Multi-view learning is necessary but not sufficient for human-like 3D shape inference.

Conclusions:

Multi-view learning objectives are crucial for improving DNNs' 3D shape inference capabilities.
Incorporating 3D inductive biases, as in Light Field Networks, enhances human-model alignment.
DNNs still face limitations in capturing human-like 3D shape inferences and generalizing to novel object categories.