AsymLoc：迈向高效视觉定位的非对称特征匹配
AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization
AI总结：
本文提出AsymLoc框架，通过几何驱动匹配目标和联合检测器-描述符蒸馏目标，实现轻量学生模型与大教师模型的非对称特征匹配，提升视觉定位效率与精度。
摘要：
精确且实时的视觉定位对于AR/VR和机器人应用至关重要，尤其是在资源受限的边缘设备如智能眼镜上，电池寿命和散热是主要关注点。尽管已有许多高效模型，但进一步减少计算量而不牺牲准确性对实际部署至关重要。为此，我们提出了非对称视觉定位：一个大教师模型在离线处理预映射数据库图像，而轻量学生模型在线处理查询图像。这在不依赖重学匹配器的情况下，提出了匹配两个不同模型特征的挑战。我们引入了AsymLoc，一种新的蒸馏框架，通过几何驱动匹配目标和联合检测器-描述符蒸馏目标，将学生模型对齐到其教师模型，实现快速、无参数的最近邻匹配。在HPatches、ScanNet、IMC2022和Aachen上的广泛实验表明，AsymLoc使用比教师模型小一个数量级的模型，实现了高达教师定位准确率的95%，显著优于现有基线，并建立了新的效率-精度权衡状态。
英文摘要：
Precise and real-time visual localization is critical for applications like AR/VR and robotics, especially on resource-constrained edge devices such as smart glasses, where battery life and heat dissipation can be a primary concerns. While many efficient models exist, further reducing compute without sacrificing accuracy is essential for practical deployment. To address this, we propose asymmetric visual localization: a large Teacher model processes pre-mapped database images offline, while a lightweight Student model processes the query image online. This creates a challenge in matching features from two different models without resorting to heavy, learned matchers. We introduce AsymLoc, a novel distillation framework that aligns a Student to its Teacher through a combination of a geometry-driven matching objective and a joint detector-descriptor distillation objective, enabling fast, parameter-less nearest-neighbor matching. Extensive experiments on HPatches, ScanNet, IMC2022, and Aachen show that AsymLoc achieves up to 95% of the teacher's localization accuracy using an order of magnitude smaller models, significantly outperforming existing baselines and establishing a new state-of-the-art efficiency-accuracy trade-off.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
