Fig. 4From: Structure from motion using dense CNN features with keypoint relocalizationQuantitative evaluation on the Aachen Day-Night dataset. The poses of night images reconstructed by the baseline DoG+RootSIFT [6] (red), the DenseCNN without keypoint relocalization (green), and the proposed DenseCNN (blue) are evaluated using the reference poses. The graphs show the percentages of correctly reconstructed camera poses of night images (y-axis) at positional (a) and angular (b) error threshold (x-axis)Back to article page