|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision.
Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring.
However, the quality of homography heavily relies on the quality of image features, which are prone to errors with respect to low light and low texture images.
By making the sampling of inlier-outlier sets from point-pair correspondences fully differentiable within the keypoint learning framework, we show that are able to simultaneously self-supervise keypoint description and improve keypoint matching.
Two new general constraints are derived on the scales and rotations which can be used in any geometric model estimation tasks.
The PF is naturally learned by the proposed fully convolutional residual network, PFNet, to keep the spatial order of each pixel.
SOTA for Homography Estimation on COCO 2014