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

A vision transformer deep learning model for assessing pediatric ileocolic intussusception severity using ultrasound images.

NPJ digital medicine·2026

Same author

AdapHBNA: Adaptive hierarchical spatio-temporal brain network analysis for brain disease detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Effects of cardiac rehabilitation on atrial fibrillation recurrence, mortality, hospitalization, and exercise capacity: a systematic review and meta-analysis.

PeerJ·2026

Same author

Activation of cryptic donor splice site due to an exonic MYPN variant in congenital myopathy.

Journal of human genetics·2026

Same author

Interpreting Pulmonary Hypertension Beyond Single Cells.

Arteriosclerosis, thrombosis, and vascular biology·2026

Same author

Functional Characterization of <i>Helicoverpa armigera</i> Nicotinic Acetylcholine Receptor Subunits Targeted by <i>cis</i>- and <i>trans</i>-Configuration Piperidine Alkaloids in <i>Solenopsis</i> Fire Ant Venom.

Journal of agricultural and food chemistry·2026

Search research articles

Related Experiment Video

Updated: Oct 18, 2025

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

SurRF: Unsupervised Multi-View Stereopsis by Learning Surface Radiance Field.

Jinzhi Zhang, Mengqi Ji, Guangyu Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence

|September 30, 2021

Summary

This study introduces SurRF, an unsupervised multi-view stereopsis method learning a Surface Radiance Field on a 2D surface. SurRF achieves competitive results without 3D supervision, overcoming limitations of prior methods.

More Related Videos

Stereoacuity Improvement using Random-Dot Video Games

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Surface Mapping of Earth-like Exoplanets using Single Point Light Curves

Surface Mapping of Earth-like Exoplanets using Single Point Light Curves

Published on: May 10, 2020

Related Experiment Videos

Last Updated: Oct 18, 2025

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

Stereoacuity Improvement using Random-Dot Video Games

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Surface Mapping of Earth-like Exoplanets using Single Point Light Curves

Surface Mapping of Earth-like Exoplanets using Single Point Light Curves

Published on: May 10, 2020

Area of Science:

Computer Vision
Computer Graphics
Geometric Deep Learning

Background:

Supervised multi-view stereopsis (MVS) requires extensive 3D data collection.
Unsupervised MVS methods using differentiable rendering often use discretized or implicit representations, limiting detail and integrity.

Purpose of the Study:

To propose SurRF, an unsupervised MVS pipeline learning a Surface Radiance Field on a continuous, explicit 2D surface.
To overcome limitations of existing unsupervised MVS techniques regarding geometric detail and texture integrity.

Main Methods:

Learning a radiance field on a 2D deformable surface using differentiable rendering.
Deforming an explicit surface locally along view-dependent camera rays.
Representing geometry and appearance on a compact 2D surface instead of a dense 3D volume.

Main Results:

SurRF achieves competitive performance against state-of-the-art methods on challenging real-world scenes.
The method successfully reconstructs scenes without requiring any 3D supervision.
Demonstrates high geometric resolution and realistic texture rendering.

Conclusions:

SurRF offers a novel unsupervised MVS approach with compact representation and high-fidelity reconstruction.
The method combines advantages of meshes, continuous surfaces, and radiance fields.
Shows potential for scene manipulation, high geometric resolution, and realistic rendering in complex scenes.