发表机构
Austrian Institute of Technology; Technical University of Braunschweig; University of Vienna（奥地利技术研究所; 布伦瑞克工业大学; 维也纳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出新型隐私保护关键点检测器Misanthrope，通过自蒸馏训练避免在人体上检测关键点以从源头缓解逆攻击，其图像匹配性能与最优方法相当，在人体干扰的挑战性场景及2021图像匹配挑战测试集上表现更优。
AI 中文摘要
图像匹配是同步定位与建图（SLAM）、视觉定位、运动恢复结构（SfM）等应用的核心组件。然而，该任务的核心局部图像特征易受逆攻击影响，攻击者可通过局部特征重构隐私敏感的场景内容，这类攻击在预计算特征从边缘设备流出至远程服务器处理的分布式计算场景中威胁尤为突出。本研究提出Misanthrope，这是一种新型隐私保护型关键点检测器，通过自蒸馏训练以避免在人体上检测关键点——人体是多数定位场景中隐私敏感内容的主要来源，从而从源头缓解逆攻击，而非通过事后混淆。我们证实传统特征检测管道生成的逆图像可用于检测和再识别场景中的人体，而Misanthrope可缓解此类攻击。此外，Misanthrope在图像匹配性能上与现有最优方法相当，且在人体作为干扰项的挑战性场景（如摄影旅游和野外里程计）中表现更优。在2021年图像匹配挑战摄影旅游测试集上，Misanthrope在9个场景中的7个场景表现为性能最优的稀疏特征提取器。我们在此提供模型及评估脚本：this https URL
英文摘要
Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion (SfM). However, the local image features central to this task are vulnerable to inversion attacks, which enable adversaries to reconstruct privacy-sensitive scene content from local features. These attacks pose a particular threat in distributed computing scenarios where the pre-computed features leave edge devices to be processed by remote servers. In this work, we introduce Misanthrope, a novel privacy-preserving keypoint detector trained through self-distillation to avoid detecting keypoints on people---a predominant source of privacy-sensitive content in most localization scenarios---thus mitigating inversion attacks at the source rather than through post-hoc obfuscation. We demonstrate how inverted images from traditional feature detection pipelines can be used to detect and re-identify people in the scene, while Misanthrope is able to mitigate these attacks. Furthermore, Misanthrope maintains image matching performance on par with the state of the art and even surpasses it in challenging settings where people act as distractors, such as phototourism and in-the-wild odometry. On the Image Matching Challenge 2021 Phototourism test set, Misanthrope is the top-performing sparse feature extractor in 7 out of 9 scenes. We make our model and its evaluation script available here: https://github.com/fratopa/misanthrope
CommentsAccepted to Privacy preserving Visual Localization (PPVLM) workshop at the European Conference on Computer Vision (ECCV) 2026
