Structure from motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the extracted CNN features which is not even pixel-level accuracy in the existing approach. Providing dense feature matches with precise keypoint positions is not trivial because of memory limitation and computational burden of dense features. To achieve accurate SfM reconstruction with highly repeatable dense features, we propose an SfM pipeline that uses dense CNN features with relocalization of keypoint position that can efficiently and accurately provide pixel-level feature correspondences. Then, we demonstrate on the Aachen Day-Night dataset that the proposed SfM using dense CNN features with the keypoint relocalization outperforms a state-of-the-art SfM (COLMAP using RootSIFT) by a large margin.

中文翻译：

---

使用具有关键点重新定位的密集CNN功能从运动构造

使用运动图像（SfM）进行结构涉及极端外观变化，这是一项艰巨的任务，因为它会损失特征的可重复性。使用通过匹配密集提取的卷积神经网络（CNN）特征获得的特征对应关系，可以显着提高SfM重建能力。但是，重建精度受到提取的CNN特征的空间分辨率的限制，在现有方法中，该分辨率甚至不是像素级精度。由于内存限制和密集特征的计算负担，为密集特征匹配提供精确的关键点位置并非易事。为了实现具有高度可重复的密集特征的精确SfM重建，我们提出了一个SfM管道，该管道使用密集的CNN特征和关键点位置的重新定位，可以高效，准确地提供像素级特征对应。然后，我们在亚琛Day-Night数据集上证明了使用密集的CNN特征和关键点重新定位的拟议SfM在很大程度上优于最新的SfM（使用RootSIFT的COLMAP）。