TILDE: A Temporally Invariant Learned DEtector
This addresses the challenge of robust keypoint detection for computer vision applications in varying environmental conditions, though it appears incremental as it builds on existing keypoint detection frameworks.
The paper tackles the problem of detecting repeatable keypoints under drastic weather and lighting changes, where state-of-the-art detectors are sensitive, and shows that their method significantly outperforms existing methods in these conditions while achieving state-of-the-art performance on standard datasets.
We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in multiple training images taken from the same viewpoint. We then train a regressor to predict a score map whose maxima are those points so that they can be found by simple non-maximum suppression. As there are no standard datasets to test the influence of these kinds of changes, we created our own, which we will make publicly available. We will show that our method significantly outperforms the state-of-the-art methods in such challenging conditions, while still achieving state-of-the-art performance on the untrained standard Oxford dataset.