Frédéric Lavoie

3D Gaussian Splatting typically collapses without dozens of views, but anchoring explicit primitives to statistical shape models unlocks robust volumetric reconstruction from just five X-ray projections.

Expensive iterative 3D-to-2D projection loops are entirely unnecessary for anatomical reconstruction: directly learning cross-dimensional deformation co-variation enables sub-3-second 3D mesh lifting from standard radiographs.