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. Image Rectangling Network Based On Reparameterized Transformer And Assisted Learning

Image rectangling network based on reparameterized transformer and assisted learning

Lichun Yang1, Bin Tian2, Tianyin Zhang1

  • 1Key Laboratory of Optoelectronic Technology and Intelligent Control, Ministry of Education, Lanzhou Jiaotong University, Gansu, Lanzhou, China.

Scientific Reports
|March 25, 2024

Related Experiment Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

395
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

718

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a novel image rectangling method using a reparameterized transformer and assisted learning. The approach effectively rectangles stitched images with irregular boundaries, preserving content fidelity and improving efficiency.

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Stitched images offer wider fields of view but often have irregular boundaries.
  • Existing rectangling methods can cause content distortion and data loss.

Purpose of the Study:

  • To develop an effective image rectangling solution for stitched images.
  • To overcome limitations of current rectangling techniques regarding distortion and boundary information loss.

Main Methods:

  • Utilized a reparameterized transformer structure for rectangling.
  • Incorporated an assisted learning network to support the rectangling process.
  • Implemented a local thin-plate spline transform for efficient local deformation and parallel processing.

Main Results:

Keywords:
Assisted learningImage rectanglingRe-parameterizationSingle wrap

Related Experiment Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

395
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

718
  • Achieved state-of-the-art performance in stitched image rectangling.
  • Maintained high content fidelity.
  • Demonstrated efficiency with a low number of parameters.

Conclusions:

  • The proposed method offers a superior solution for rectangling stitched images.
  • The approach effectively addresses irregular boundaries while preserving image content.
  • The method presents a computationally efficient and high-fidelity rectangling technique.