SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning 事件

SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning arXiv:2606.04493v1 Announce Type: new Abstract: Correspondence pruning aims to identify inliers from an initial set of correspondences. Most existing Graph Neural Network (GNN)-based methods rely on geometric features mapped from coarse Euclidean coordinates, which struggle to capture the subtle geometric consistencies presented by inliers. While Mamba-based methods possess global receptive fields and