论文标题
用于定向关键点检测的自我监督的模棱两可的学习
Self-Supervised Equivariant Learning for Oriented Keypoint Detection
论文作者
论文摘要
从图像中检测强大的关键点是许多计算机视觉问题不可或缺的一部分，而关键点的特征方向和规模对于关键点描述和匹配起着重要作用。现有的基于学习的关键点检测方法取决于标准的翻译等值CNN，但通常无法检测到可靠的关键点针对几何变化。为了学习检测稳健的定向关键，我们使用旋转式的CNN引入了一个自我监督的学习框架。我们通过合成转换产生的图像对提出了密集的方向对齐损失，以训练基于直方图的方向图。我们的方法的表现优于匹配基准和摄像头姿势估计基准的图像匹配的先前方法。
Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.
