Raysemble: Metric 3D Bone Reconstruction from a Single X-ray

Xiaoyang Li, Xinghao Yan, Yuan Chai

Abstract

Raysemble reconstructs eight lumbar and pelvic bones from a single X-ray by separating shape and placement. Each 3D query samples regional and global features at its image projection. A shared decoder predicts normalized bone shapes. Predicted depth and camera geometry determine 3D centers and scales for resampling these shapes onto a common grid in millimeters. Evaluation uses 23 held-out patients with 43 CT scans, each generating one simulated anteroposterior radiograph. Without rigid alignment to CT,Raysemble leads 15 evaluated methods, averaging 65.24% Dice, 9.09 mm HD95, and 3.32 mm ASSD over three random seeds. With identical inputs, it improves Dice over VolumeNeRF by 5.86 percentage points.
BibTeX
@misc{li2026raysemble,
  author = {Xiaoyang Li and Xinghao Yan and Yuan Chai},
  title = {{Raysemble: Metric 3D Bone Reconstruction from a Single X-ray}},
  year = {2026},
  eprint = {2611.16869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.16869},
}

Loading related content...

Figure