HR-APR：具有不确定性估计与层次化精修的APR无关相机重定位框架
HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation
AI总结：
提出APR无关框架HR-APR，通过余弦相似度估计不确定性并用于位姿精修，在保持SOTA精度的同时显著降低计算开销。
摘要：
绝对位姿回归器（APRs）直接从单目图像估计相机位姿，但其精度对不同查询而言不稳定。不确定性感知的APRs提供关于估计位姿的不确定性信息，减轻了这些不可靠预测的影响。然而，现有的不确定性建模技术往往与特定的APR架构耦合，导致其性能相较于最先进的（SOTA）APR方法有所不足。本工作引入了一种新颖的APR无关框架HR-APR，将不确定性估计表述为查询特征与数据库特征之间的余弦相似度估计。它不依赖也不影响APR网络架构，灵活且计算高效。此外，我们利用不确定性进行位姿精修以增强APR的性能。大量实验证明了我们框架的有效性，在7Scenes和Cambridge Landmarks数据集上分别减少了27.4%和15.2%的计算开销，同时保持了单图像APR的SOTA精度。
英文摘要：
Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4\% and 15.2\% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs.
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。
