RaCo通过排名与协方差机制，实现无需配对图像的鲁棒关键点检测。
RaCo: Ranking and Covariance for Practical Learned Keypoints
- 用可微分排名器优化关键点数量，提升匹配效率。
- 在大平面旋转下仍保持高重复率，优于现有方法。
- 无需额外标注，可同时输出关键点排序与空间不确定性。
本文提出RaCo，一种轻量级神经网络，用于学习适用于多种3D视觉任务的鲁棒且通用的关键点。模型融合三个核心组件：可重复关键点检测器、可微分排名器以在有限关键点数下最大化匹配，以及协方差估计器以量化度量尺度下的空间不确定性。仅在透视图像块上训练，无需共可见图像对。通过大规模数据增强实现强旋转鲁棒性，无需计算昂贵的等变网络结构。在多个挑战性数据集上评估，其在关键点重复性和两视图匹配方面表现卓越，尤其在大平面旋转下优势明显。最终，RaCo提供了一种独立估计关键点排名与度量协方差的有效且简洁策略，无需额外标签，可检测可解释且可重复的兴趣点。代码已公开于https://github.com/cvg/RaCo。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。