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 Experiment Videos

Image stitching using structure deformation.

Jiaya Jia1, Chi-Keung Tang

  • 1Department of Computer Science and Engineering, Chinese University of Hong Kong, Shatin, N.T., Hong Kong. leojia@cse.cuhk.edu.hk

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 16, 2008
PubMed
Summary
This summary is machine-generated.

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

Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

TagCLIP: Improving Discrimination Ability of Zero-Shot Semantic Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

MOODv2: Masked Image Modeling for Out-of-Distribution Detection.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

BAL: Balancing Diversity and Novelty for Active Learning.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

PFENet++: Boosting Few-Shot Semantic Segmentation With the Noise-Filtered Context-Aware Prior Mask.

IEEE transactions on pattern analysis and machine intelligence·2023
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a novel image stitching method using structure deformation and propagation to eliminate visual artifacts from intensity and structure misalignment. The approach ensures seamless results in image compositing and blending applications.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Photography

Background:

  • Image stitching often suffers from visual artifacts due to intensity discrepancies and structural misalignments, especially with roughly aligned inputs.
  • Existing methods struggle to maintain overall consistency in both image structure and intensity during the stitching process.

Purpose of the Study:

  • To develop a seamless image stitching technique that effectively addresses visual artifacts caused by severe intensity discrepancy and structure misalignment.
  • To achieve overall consistency in image structure and intensity through a novel approach based on structure deformation and propagation.

Main Methods:

  • The algorithm computes optimal partitions based on 2-D feature compatibility, ensuring intensity coherence and structure continuity.

Related Experiment Videos

  • It detects 1-D features along partitions to derive sparse deformation vectors for robust feature matching.
  • Deformation cues are propagated into input images via gradient domain minimization for simultaneous structure and intensity alignment.

    • Main Results:

    • The proposed method successfully produces seamless stitching results, even from complex input images with significant differences.
    • Demonstrated effectiveness in general image compositing and blending applications, mitigating common stitching artifacts.
    • The gradient domain propagation framework uniformly aligns image structure and intensity.

    Conclusions:

    • The structure deformation and propagation approach offers a robust solution for seamless image stitching, overcoming limitations of existing methods.
    • The technique effectively handles intensity discrepancy and structure misalignment, leading to high-quality composite images.
    • This method provides a unified framework for simultaneous alignment of image structure and intensity, enhancing image compositing and blending quality.