cs.CVNov 12, 2026

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

Authors: Xiaoyang Li, Xinghao Yan, Yuan Chai

Organizations: ORBIT Lab, College of Medicine and Biomedical Information Engineering, Northeastern University, Shenyang 110016, China · The John Curtin School of Medical Research, College of Science and Medicine, Australian National University, Canberra 2601, Australia

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.

Figures & tables

Explore similar work

CardsList
  1. Learning Dense 2D-3D Correspondence for X-ray-to-CT Registration of Knee Bones

    Jul 24, 2026Rembert Daems, Jonas Grammens, Caro Roten +32D-3D Image RegistrationMedical Image Registration

  2. A New Angle on Bones: Robust Pose Estimation in X-Ray and Ultrasound

    Jun 3, 2026Ron Keuth, Christoph Großbröhmer, Franziska Halm +5Medical Image AnalysisRobust Estimation

  3. A Joint 2D-3D Statistical Shape Model for Orthopedic Reconstruction

    Sep 8, 2026Florence Dell'Aniello Picard, Pranav Poudel, Nairouz Shehata +23D Reconstruction3D Medical Imaging