Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale-equivariance are both critical in correspondence matching applications. Classical correspondence matching approaches are designed to withstand scaling and rotation transformations. However, the features extracted using convolutional neural networks (CNNs) are only translation-equivariant to a certain extent. Recently, researchers have strived to improve the rotation-equivariance of CNNs based on group theories. Sim(2) is the group of similarity transformations in the 2D plane. This paper presents a specialized dataset dedicated to evaluating sim(2)-equivariant correspondence matching algorithms. We compare the performance of 16 state-of-the-art (SoTA) correspondence matching approaches. The experimental results demonstrate the importance of group equivariant algorithms for correspondence matching on various sim(2) transformation conditions. Since the subpixel accuracy achieved by CNN-based correspondence matching approaches is unsatisfactory, this specific area requires more attention in future works. Our dataset is publicly available at: mias.group/SIM2E.
翻译:通信匹配是计算机视觉和机器人应用中的一个基本问题。 使用神经网络解决匹配问题的通信问题最近呈上升趋势。 在通信匹配应用程序中,旋转- 均匀和比例- 均匀都至关重要。 古典通信匹配方法旨在抵御缩放和旋转转换。 但是, 使用进化神经网络( CNNs) 提取的特征在一定程度上只是翻译- Qevarial。 最近, 研究人员努力根据群体理论改进CNNs的旋转- 均匀性能。 Sim(2) 是 2D 平面的相似性变换组。 本文展示了一个专门用来评价 im(2) 等式通信匹配算法的专门数据集。 我们比较了十六种最新( SoTA) 对应法的性能。 实验结果显示, 组别间静态算法对于各种im(2) 转换条件的对应性能十分重要。 由于基于CNN 通信匹配方法的子像素精度不令人满意, 此特定区域需要在未来工作中给予更多关注。 我们的数据设置在 MI: MI / 。