Current deep visual local feature detectors do not model the spatial uncertainty of detected features, producing suboptimal results in downstream applications. In this work, we propose two post-hoc covariance estimates that can be plugged into any pretrained deep feature detector: a simple, isotropic covariance estimate that uses the predicted score at a given pixel location, and a full covariance estimate via the local structure tensor of the learned score maps. Both methods are easy to implement and can be applied to any deep feature detector. We show that these covariances are directly related to errors in feature matching, leading to improvements in downstream tasks, including solving the perspective-n-point problem and motion-only bundle adjustment. Code is available at https://github.com/javrtg/DAC

翻译：当前深度视觉局部特征检测器未对检测到的特征进行空间不确定性建模，导致在下游应用中产生次优结果。本文提出两种可插入任意预训练深度特征检测器的后验协方差估计方法：其一为简单各向同性协方差估计，利用给定像素位置的预测得分；其二为通过所学得分图局部结构张量实现的完全协方差估计。两种方法均易于实现且适用于任何深度特征检测器。实验表明，这些协方差与特征匹配误差直接相关，能有效改进下游任务，包括解决透视n点问题和仅运动束调整。代码开源在https://github.com/javrtg/DAC