重新审视几何混淆：用于视觉定位中隐私保护图像查询的双收敛线
Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization
DCL 通过双收敛线设计使几何恢复攻击的优化问题变得病态，为视觉定位中的隐私保护提供了一种可部署的关键点混淆方案，可直接集成到基于线段的定位求解器中。
原文依据 DCL places two fixed anchors on a central partition line and lifts each keypoint to a line originating from one of them
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论隐私保护图像查询（PPIQ）是一种新兴的云端视觉定位机制，能够从混淆特征而非私有图像或原始关键点中进行姿态估计。然而，PPIQ 的主要方法——基于几何和基于分割的混淆——都容易受到近期隐私攻击的影响。特别是，基于几何的混淆的一个基本限制是，混淆后的邻近线的空间分布仍然有效地包围了原始关键点位置，为恢复原始点提供了可利用的线索。我们重新审视这一几何范式，并引入双收敛线（DCL），一种新颖的关键点混淆方法，对此类攻击表现出强韧性。DCL 在中心分割线上放置两个固定锚点，并将每个关键点提升到源自其中一个锚点的线上，活动锚点由关键点的位置决定。这种安排通过使其优化问题变得病态而使几何恢复攻击失效：邻近线要么误导性地收敛到一个锚点，产生平凡解，要么在分割边界处变得近乎平行，产生不稳定的高方差解。这两种结果都阻止了点恢复。DCL 还与现有的基于线的求解器兼容，从而能够部署在传统的定位流程中。在室内和大规模室外数据集上的实验证明了 DCL 对隐私攻击的鲁棒性、效率和可扩展性，同时实现了实用的定位性能。
英文原文摘要 1597 字符
Privacy-Preserving Image Queries (PPIQ) are an emerging mechanism for cloud-based visual localization, enabling pose estimation from obfuscated features instead of private images or raw keypoints. However, the main approaches for PPIQ, primarily geometry-based and segmentation-based obfuscation, both suffer from vulnerabilities to recent privacy attacks. In particular, a fundamental limitation of geometry-based obfuscation is that the spatial distribution of obfuscated neighboring lines still effectively surrounds the original keypoint location, providing exploitable cues for recovering the original points. We revisit this geometric paradigm and introduce Dual Convergent Lines (DCL), a novel keypoint obfuscation method demonstrating strong resilience against such attack. DCL places two fixed anchors on a central partition line and lifts each keypoint to a line originating from one of them, with the active anchor determined by the keypoint's location. This arrangement invalidates the geometry-recovery attack by making its optimization ill-posed: Neighboring lines either misleadingly converge to one anchor, yielding a trivial solution, or become near-parallel at the partition boundary, yielding an unstable high-variance solution. Both outcomes thwart point recovery. DCL is also compatible with an existing line-based solver, enabling deployment in traditional localization pipelines. Experiments on both indoor and large-scale outdoor datasets demonstrate DCL's robustness against privacy attacks, efficiency, and scalability, while achieving practical localization performance.