• Home
  • Search
  • Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks
  • Cite Icon11
  • https://doi.org/10.1609/aaai.v38i3.28036Copy DOI Icon

Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Image stitching seamlessly integrates images captured from varying perspectives into a single wide field-of-view image. Such integration not only broadens the captured scene but also augments holistic perception in computer vision applications. Given a pair of captured images, subtle perturbations and distortions which go unnoticed by the human visual system tend to attack the correspondence matching, impairing the performance of image stitching algorithms. In light of this challenge, this paper presents the first attempt to improve the robustness of image stitching against adversarial attacks. Specifically, we introduce a stitching-oriented attack (SoA), tailored to amplify the alignment loss within overlapping regions, thereby targeting the feature matching procedure. To establish an attack resistant model, we delve into the robustness of stitching architecture and develop an adaptive adversarial training (AAT) to balance attack resistance with stitching precision. In this way, we relieve the gap between the routine adversarial training and benign models, ensuring resilience without quality compromise. Comprehensive evaluation across real-world and synthetic datasets validate the deterioration of SoA on stitching performance. Furthermore, AAT emerges as a more robust solution against adversarial perturbations, delivering superior stitching results. Code is available at: https://github.com/Jzy2017/TRIS.

Similar Papers
  • Research Article
  • Citations20

Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training

  • Jun 01, 2022
  • IEEE Transactions on Cognitive Communications and Networking
  • B R Manoj +2
  • Research Article
  • Citations3

Enhancing Model Robustness and Accuracy Against Adversarial Attacks via Adversarial Input Training

  • Jan 01, 2024
  • International Journal of Advanced Computer Science and Applications
  • Ganesh Ingle +1
  • Conference Article
  • Citations10

Towards Adversarially Robust Deep Image Denoising

  • Jul 01, 2022
  • Hanshu Yan +4
  • Research Article
  • Citations10

CardioDefense: Defending against adversarial attack in ECG classification with adversarial distillation training

  • Jan 05, 2024
  • Biomedical Signal Processing and Control
  • Jiahao Shao +5
  • Research Article
  • Citations7

Adversarial attacks and active defense on deep learning based identification of GaN power amplifiers under physical perturbation

  • Dec 02, 2022
  • AEU - International Journal of Electronics and Communications
  • Yuqing Xu +4
  • Conference Article
  • Citations5

Adversarial joint attacks on legged robots

  • Oct 09, 2022
  • Takuto Otomo +2
  • Conference Article
  • Citations146

Rob-GAN: Generator, Discriminator, and Adversarial Attacker

  • Jun 01, 2019
  • Xuanqing Liu +1
  • PDF
  • Research Article
  • Citations1

Improving Model Robustness through Hybrid Adversarial Training: Integrating FGSM and PGD Methods

  • Nov 26, 2024
  • Applied and Computational Engineering
  • Zeshan Zhong
  • Research Article
  • Citations112

Image stitching by line-guided local warping with global similarity constraint

  • Jun 22, 2018
  • Pattern Recognition
  • Tian-Zhu Xiang +3
  • Research Article
  • Citations2

PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Ximin Zhang +3
  • Research Article

AMAKD: Adversarial multi-modal attention-based knowledge distillation for robust behaviour anomaly detection in real-world environments

  • Apr 01, 2026
  • Alexandria Engineering Journal
  • Maram Fahaad Almufareh
  • Conference Article
  • Citations67

Defending Against Universal Perturbations With Shared Adversarial Training

  • Oct 01, 2019
  • Chaithanya Kumar Mummadi +2
  • Research Article
  • Citations16

Robust Attacks Detection Model for Internet of Flying Things Based on Generative Adversarial Network (GAN) and Adversarial Training

  • Jul 01, 2025
  • IEEE Internet of Things Journal
  • Tarek Gaber +3
  • Research Article
  • Citations3

Security Enhancement of mmWave MIMO Wireless Communication System Using Adversarial Training

  • Feb 21, 2024
  • IEEJ Transactions on Electrical and Electronic Engineering
  • Mehak Saini +1
  • PDF
  • Conference Article
  • Citations115

On the Robustness of Self-Attentive Models

  • Jan 01, 2019
  • Yu-Lun Hsieh +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.