Seed to Prune: A Seeded Graph Neural Network for Two-View Correspondence Learning
We present a simple yet tough-to-beat method dubbed SGNNet, for correspondence
learning. Instead of focusing on devising sophisticated geometric extractors to explore the …
learning. Instead of focusing on devising sophisticated geometric extractors to explore the …
DiffGlue: Diffusion-Aided Image Feature Matching
As one of the most fundamental computer vision problems, image feature matching aims to
establish correct correspondences between two-view images. Existing studies enhance the …
establish correct correspondences between two-view images. Existing studies enhance the …