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

  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Graphics, Augmented Reality And Games
  9. Computer Aided Design
  11. Reusable Architecture Growth For Continual Stereo Matching.
  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Graphics, Augmented Reality And Games
  9. Computer Aided Design
  11. Reusable Architecture Growth For Continual Stereo Matching.

Related Experiment Video

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

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

Published on: August 12, 2021

2.0K

Reusable Architecture Growth for Continual Stereo Matching.

Chenghao Zhang, Gaofeng Meng, Bin Fan

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 19, 2024

    View abstract on PubMed

    Summary
    This summary is machine-generated.

    This study introduces a Reusable Architecture Growth (RAG) framework for continual stereo matching. It enables models to learn new scenes without forgetting old ones, improving disparity prediction for real-world applications.

    More Related Videos

    Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
    07:03

    Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

    Published on: February 23, 2017

    7.7K
    Stereoacuity Improvement using Random-Dot Video Games
    06:25

    Stereoacuity Improvement using Random-Dot Video Games

    Published on: January 14, 2020

    14.3K

    Related Experiment Videos

    Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
    05:12

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

    Published on: August 12, 2021

    2.0K
    Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
    07:03

    Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

    Published on: February 23, 2017

    7.7K
    Stereoacuity Improvement using Random-Dot Video Games
    06:25

    Stereoacuity Improvement using Random-Dot Video Games

    Published on: January 14, 2020

    14.3K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Deep Learning

    Background:

    • Recent stereo depth estimation models utilize convolutional neural networks for dense disparity regression.
    • Continuous acquisition of training data in practical applications necessitates continual learning capabilities for models.
    • Existing models often struggle with forgetting previously learned scenes when adapting to new data.

    Purpose of the Study:

    • To develop a continual stereo matching framework capable of learning new scenes, preventing catastrophic forgetting, and performing continuous disparity prediction.
    • To introduce a novel Reusable Architecture Growth (RAG) framework for adaptive and efficient continual learning in stereo matching.
    • To enhance the adaptability of stereo depth estimation models for practical, real-world deployment.

    Main Methods:

    • Proposed a Reusable Architecture Growth (RAG) framework employing task-specific neural unit search and architecture growth.
    • Implemented both supervised and self-supervised learning approaches within the RAG framework for continual scene learning.
    • Introduced a Scene Router module for adaptive selection of scene-specific architectural paths during inference.

    Main Results:

    • The RAG framework demonstrated high reusability of previous neural units while achieving strong performance on new scenes.
    • The proposed method significantly outperformed state-of-the-art methods, especially in challenging cross-dataset scenarios.
    • Experiments confirmed the framework's impressive performance across diverse environmental conditions (weather, road, city).

    Conclusions:

    • The RAG framework effectively addresses the challenge of continual stereo matching, enabling models to adapt to new scenes without forgetting.
    • The Scene Router module enhances inference adaptability, facilitating end-to-end stereo architecture learning.
    • This approach holds significant potential for practical deployment in real-world stereo depth estimation applications.