Preprint
Sep 2026
XPos3R: Cross-Modal Transformer for Intraoperative 2D/3D Registration
This work proposes XPos3R, a generalizable pose regression method that eliminates preoperative preparation, and introduces an asymmetric encoder-decoder architecture that improves cross-modal feature alignment while maintaining computational efficiency.
Shi-Yan Su, Ruyi Zha, Hong-Dong Li et al.
· 0 citations