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.

翻译：绝对位姿回归器（APRs）可直接从单目图像估计相机位姿，但其对不同查询的精度存在不稳定性。具有不确定性感知的APR能提供估计位姿的不确定性信息，从而缓解不可靠预测的影响。然而，现有不确定性建模技术常与特定APR架构耦合，导致其性能逊色于最先进的APR方法。本文提出一种新颖的APR无关框架HR-APR，该方法将不确定性估计建模为查询与数据库特征之间的余弦相似度估计，既不依赖也不影响APR网络架构，具有灵活性和计算高效性。此外，我们利用不确定性进行位姿优化以提升APR性能。大量实验证明了本框架的有效性：在7Scenes和Cambridge Landmarks数据集上分别减少27.4%和15.2%的计算开销，同时保持单图像APR的最先进精度。