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

TL;DR

This paper introduces a novel adversarial attack method for image stitching and proposes an adaptive adversarial training approach to enhance the robustness of stitching algorithms against such attacks, ensuring high-quality results.

Contribution

It presents the first stitching-oriented attack and an adaptive adversarial training method to improve robustness without sacrificing stitching quality.

Findings

SoA significantly degrades stitching performance under attack.

AAT improves robustness against adversarial perturbations.

Proposed methods outperform existing approaches in experiments.

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.