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

Search research articles

Related Experiment Video

Updated: May 28, 2026

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

Sparse Self-Prompt-Guided Stereo Matching for Real-World Generalization.

Hangbiao Li^1,2, Haojun Mo², Xing Li¹

¹School of Information and Engineering, Nanchang Hangkong University, Nanchang 330063, China.

Sensors (Basel, Switzerland)

|May 27, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

OOM-ORL-ROOF Composite Flap Suspension (ORRCS) to the Lateral Orbital Thickening for Lateral Hooding.

Aesthetic plastic surgery·2026

Same author

A C3 Radical Copolymerization.

Polymer science & technology (Washington, D.C.)·2026

Same author

Programmable, multiplexed and orthogonal gene control in bacteria with attenuated Cas13d systems.

Nature biotechnology·2026

Same author

Inheritable Epigenetic Memory Induced by Parental Salt Stress Influences Transgenerational Plasticity of <i>Phragmites australis</i>.

Ecology and evolution·2026

Same author

Probing molecular diversity and ultrastructure of brain cells with fluorescent aptamers.

Nature communications·2026

Same author

A critical review on the application of peracetic acid in waste activated sludge treatment.

Journal of environmental management·2026

This study introduces a novel sparse self-prompt-guided network (SSPGNet) for robust stereo matching. The method enhances generalization in real-world scenarios by using a sparse disparity map to guide dense disparity prediction.

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Stereo matching models excel on benchmarks but struggle in real-world, unconstrained environments.
Deploying stereo matching models in diverse conditions requires robust generalization capabilities.

Purpose of the Study:

To present a novel sparse self-prompt-guided network (SSPGNet) for stereo matching.
To improve the generalization of stereo matching models across diverse indoor and outdoor environments.
To enable direct deployment of stereo matching in real-world perception systems.

Main Methods:

Introduced a sparse self-prompt guidance mechanism using a self-estimated sparse disparity map from visual foundation model features.
Employed a sparse-to-dense prediction approach, refining sparse disparity into dense maps via cross-attention stereo feature interaction.

Keywords:

disparity estimation domain generalization real-world perception sparse prompt stereo matching vision foundation models

More Related Videos

Stereoacuity Improvement using Random-Dot Video Games

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Related Experiment Videos

Last Updated: May 28, 2026

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

Stereoacuity Improvement using Random-Dot Video Games

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

Collected a diverse dataset of indoor and outdoor stereo pairs using a ZED 2 camera for real-world evaluation.

Main Results:

SSPGNet demonstrated strong performance on public benchmarks (KITTI, Middlebury, ETH3D) and the in-the-wild dataset.
Achieved top rankings on three out of four public benchmarks under a cross-domain (zero-shot) protocol.
Showcased preservation of semantic awareness from visual foundation models and enhanced stereo correspondence reasoning.

Conclusions:

The proposed sparse-to-dense prompt mechanism significantly enhances stereo matching performance and generalization.
SSPGNet shows great potential for real-world stereo perception system deployment.
The model's ability to generalize across diverse environments addresses a key challenge in stereo matching.