xvr: X-ray to Volume Registration

Training patient-specific 2D/3D registration models in 5 minutes.
• 🚀 A single CLI/API for training models and registering clinical data
• ⚡️ 100x faster patient-specific model training than DiffPose
• 📐 Submillimeter registration accuracy with new image-similarity metrics
• 🐍 Pure Python/PyTorch implementation

Manuscript

Rapid patient-specific neural networks for intraoperative X-ray to volume registration.
Vivek Gopalakrishnan, Neel Dey, David-Dimitris Chlorogiannis, Andrew Abumoussa, Anna M. Larson, Darren B. Orbach, Sarah Frisken, Polina Golland
arXiv: https://arxiv.org/abs/2503.16309

Software

https://github.com/eigenvivek/xvr

Documentation

https://github.com/eigenvivek/xvr#usage

Pretrained Models

https://huggingface.co/eigenvivek/xvr