Search research articles

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.

Perceptual Constancy

Perceptual Constancy

Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...

You might also read

Related Articles

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

Sort by

Same author

Homography-Based Minimal-Case Relative Pose Estimation With Known Gravity Direction.

IEEE transactions on pattern analysis and machine intelligence·2020

Same author

Learning Semantic Correspondence Exploiting an Object-Level Prior.

IEEE transactions on pattern analysis and machine intelligence·2020

Same author

When Dijkstra Meets Vanishing Point: A Stereo Vision Approach for Road Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018

Same author

Proposal Flow: Semantic Correspondences from Object Proposals.

IEEE transactions on pattern analysis and machine intelligence·2017

Same author

Robust Guided Image Filtering Using Nonconvex Potentials.

IEEE transactions on pattern analysis and machine intelligence·2017

Same author

Task-driven dictionary learning.

IEEE transactions on pattern analysis and machine intelligence·2011

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

Search research articles

Related Experiment Video

Updated: Jun 12, 2026

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

Accurate, dense, and robust multiview stereopsis.

Yasutaka Furukawa¹, Jean Ponce

¹Google Inc., Seattle, WA 98103, USA. furukawa@cs.washington.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|June 19, 2010

Summary

This study introduces a new multiview stereopsis algorithm for dense 3D surface reconstruction. The method excels at handling complex scenes and details, outperforming existing approaches on benchmark datasets.

More Related Videos

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Related Experiment Videos

Last Updated: Jun 12, 2026

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

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

Area of Science:

Computer Vision
3D Reconstruction
Computational Geometry

Background:

Multiview stereopsis is crucial for creating 3D models from 2D images.
Existing methods often struggle with complex scenes, fine details, and occlusions.
Initialization requirements can limit the applicability of current stereopsis algorithms.

Purpose of the Study:

To develop a novel, robust algorithm for dense multiview stereopsis.
To improve 3D surface reconstruction accuracy and efficiency.
To eliminate the need for manual initialization or prior scene knowledge.

Main Methods:

A match-expand-filter procedure using keypoints for initial sparse matching.
Enforcement of local photometric consistency and global visibility constraints for accurate patch expansion.
Mesh generation and refinement using photometric consistency and regularization.

Main Results:

The algorithm generates dense, accurate 3D surface patches.
It automatically handles outliers, obstacles, and complex structures (fine details, concavities, thin structures).
Outperformed existing methods on 4 out of 6 datasets in the Middlebury benchmark.

Conclusions:

The proposed multiview stereopsis algorithm offers a significant advancement in 3D reconstruction.
Its robustness and lack of initialization requirements make it widely applicable.
The method demonstrates state-of-the-art performance on challenging datasets.