This paper introduces RaCo, a lightweight neural network designed to learn robust and versatile keypoints suitable for a variety of 3D computer vision tasks. The model integrates three key components: the repeatable keypoint detector, a differentiable ranker to maximize matches with a limited number of keypoints, and a covariance estimator to quantify spatial uncertainty in metric scale. Trained on perspective image crops only, RaCo operates without the need for covisible image pairs. It achieves strong rotational robustness through extensive data augmentation, even without the use of computationally expensive equivariant network architectures. The method is evaluated on several challenging datasets, where it demonstrates state-of-the-art performance in keypoint repeatability and two-view matching, particularly under large in-plane rotations. Ultimately, RaCo provides an effective and simple strategy to independently estimate keypoint ranking and metric covariance without additional labels, detecting interpretable and repeatable interest points. The code is available at https://github.com/cvg/RaCo.

翻译：本文提出RaCo，一种轻量级神经网络，旨在学习适用于多种三维计算机视觉任务的鲁棒且通用的关键点。该模型整合了三个核心组件：可重复关键点检测器、用于在有限关键点数量下最大化匹配的可微分排序器，以及用于量化度量尺度下空间不确定性的协方差估计器。RaCo仅通过透视图像裁剪进行训练，无需依赖共视图像对。即使未使用计算代价高昂的等变网络架构，该方法仍能通过大规模数据增强实现强大的旋转鲁棒性。在多个具有挑战性的数据集上的评估表明，该方法在关键点可重复性与双视图匹配任务中取得了最先进的性能，尤其在大平面内旋转条件下表现突出。最终，RaCo提供了一种有效而简洁的策略，可在无需额外标注的情况下独立估计关键点排序与度量协方差，从而检测可解释且可重复的兴趣点。代码发布于https://github.com/cvg/RaCo。