The superpoint loss function constrains and predicts superpoint correspondences located in the overlapping region, while the dense point loss function directly enforces the architecture to predict dense correspondences. 2.6.1. Superpoint Correspondences Loss Function We utilize the overlapping circle loss ...
It presents a geometric Transformer for learning global features and introduces the overlap circle loss function, treating superpoint feature learning as metric learning. By combining this approach with the Sinkhorn method, GeoTransformer achieves point cloud registration without the need for RANSAC [8]....