Uncertainty Aware Interest Point Detection and Description

Interest point detection and description play an important role in many visual tasks, including image registration, pose estimation, 3D reconstruction, and more. State-of-the-art interest point detection techniques are based on deep neural networks (NNs), which are prone to produce overconfident predictions. However, calibrated and ro-bust uncertainty measurement is crucial when deploying deep NN models in safety critical applications. In this work, we propose a novel Uncertainty-Aware interest Point (UAPoint) detection method to address this problem. Our method leverages evidential learning to learn both aleatoric and epistemic uncertainty. We further propose a constrained sampling scheme to construct more efficient training pairs for the descriptor decoder. We evaluate our method on a wide range of benchmarks and show that our method achieves state-of-the-art performance. Code will be released in https://github.com/JingboZeng/UAPoint.