Conference
Sep 2026
BAG-Net: Bidirectional Receptive-Field Graph Network for Two-View Correspondence Pruning
Learning reliable two-view correspondences is essential for geometric computer vision applications. Existing graph-based pruning methods typically aggregate information unidirectionally, capturing only whether a correspondence receives neighborhood support while ignoring its structural contribution during aggregation....
Le-Yi Wang, Hao Chen, Chang-Cai Yang
· Proceedings of the Thirty-Fi... · 0 citations