Preprint
Aug 2026
Ordered Diffusion for 3D Human Registration
This work proposes ODin, which formulates registration as a 3D diffusion process that generates a point cloud aligned with the target geometry while preserving template semantics through consistent point ordering, and establishes a new state of the art in 3D human registration.
Mattia Masiero, Ilya A. Petrov, Daniel Cremers et al.
· 1 citation