AI RESEARCH

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

arXiv CS.CV

ArXi:2604.21575v1 Announce Type: new Fitting an underlying body model to 3D clothed human assets has been extensively studied, yet most approaches focus on either single-modal inputs such as point clouds or multi-view images alone, often requiring a known metric scale. This constraint is frequently impractical, especially for AI-generated assets where scale distortion is common.