用对称纹理干扰姿态估计，让模型在真实场景中出错。
Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures
- 设计多叶径向对称纹理，跨视角保持相似性以误导模型。
- 优化后攻击使多种姿态估计算法误差提升超40%。
- 适合研究模型鲁棒性或对抗样本的开发者参考。
相机姿态估计是视觉定位和多视图立体重建等应用的基础任务。在以物体为中心、输入稀疏的场景中，占据图像主要区域的背景纹理会显著影响姿态估计精度。为此，本文提出全景背景攻击（Kaleidoscopic Background Attack, KBA），利用相同片段构建具有多叶径向对称性的圆盘结构。这些圆盘在不同视角下保持高度相似性，即使使用自然纹理片段也能有效攻击姿态估计模型。此外，引入投影方向一致性损失以优化全景纹理，显著提升攻击效果。实验表明，经过优化的对抗性全景背景可有效攻破多种相机姿态估计算法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。