Uncertainty Aware Interest Point Detection and Description

Jingbo Zeng, Zaiwang Gu, Weide Liu, Lile Cai, Jun Cheng; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 2144-2153

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 robust 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 upon publication. Code will be released in https://github.com/JingboZeng/ UAPoint.