用大模型提特征，小模型快速定位，精度不降反升。
AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization
- 大模型离线处理数据库图，小模型在线处理查询图，实现异构匹配。
- 在多个数据集上仅用十分之一模型量，达到教师模型95%的定位精度。
- 无需复杂匹配器，直接近邻搜索即可，适合智能眼镜等边缘设备。
精确且实时的视觉定位对AR/VR和机器人应用至关重要，尤其在电池寿命与散热受限的边缘设备（如智能眼镜）上。尽管已有诸多高效模型，但进一步降低计算开销而不牺牲精度仍是实际部署的关键。为此，我们提出异构视觉定位：由大型教师模型离线处理预映射的数据库图像，轻量级学生模型在线处理查询图像。这带来了来自两不同模型特征匹配的挑战，而无需依赖复杂的可学习匹配器。我们提出AsymLoc，一种新型蒸馏框架，通过几何驱动的匹配目标与检测器-描述子联合蒸馏目标，使学生模型与教师模型对齐，实现快速、无参数的最近邻匹配。在HPatches、ScanNet、IMC2022和Aachen上的大量实验表明，AsymLoc仅使用教师模型数量级的十分之一，即达到其95%的定位精度，显著优于现有基线，建立了新的效率-精度权衡标杆。
原文摘要 · Abstract (English)
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.
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。