Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures

TL;DR

This paper introduces the Kaleidoscopic Background Attack (KBA), a novel method that uses symmetric textures to disrupt camera pose estimation by creating highly similar background segments across viewpoints.

Contribution

The paper proposes a new attack method using multi-fold radial symmetry textures and a projected orientation consistency loss to effectively compromise pose estimation models.

Findings

KBA significantly reduces pose estimation accuracy.

Optimized kaleidoscopic backgrounds successfully attack various models.

The method enhances attack effectiveness with symmetry-based textures.

Abstract

Camera pose estimation is a fundamental computer vision task that is essential for applications like visual localization and multi-view stereo reconstruction. In the object-centric scenarios with sparse inputs, the accuracy of pose estimation can be significantly influenced by background textures that occupy major portions of the images across different viewpoints. In light of this, we introduce the Kaleidoscopic Background Attack (KBA), which uses identical segments to form discs with multi-fold radial symmetry. These discs maintain high similarity across different viewpoints, enabling effective attacks on pose estimation models even with natural texture segments. Additionally, a projected orientation consistency loss is proposed to optimize the kaleidoscopic segments, leading to significant enhancement in the attack effectiveness. Experimental results show that optimized adversarial kaleidoscopic backgrounds can effectively attack various camera pose estimation models.