Data association is important in the point cloud registration.
Last, we propose a Feature Identity Loss (FIL) to enforce the learned image feature warp-equivariant, meaning that the result should be identical if the order of warp operation and feature extraction is swapped.
Occlusion is an inevitable and critical problem in unsupervised optical flow learning.
Deep homography methods, on the other hand, are free from such problem by learning deep features for robust performance.
Homography estimation is a basic image alignment method in many applications.
Ranked #5 on Homography Estimation on S-COCO