AI RESEARCH

Globally Optimal Pose from Orthographic Silhouettes

arXiv CS.CV

ArXi:2604.09199v1 Announce Type: new We solve the problem of determining the pose of known shapes in $\mathbb{R}^3$ from their unoccluded silhouettes. The pose is determined up to global optimality using a simple yet under-explored property of the area-of-silhouette: its continuity w.r.t trajectories in the rotation space. The proposed method utilises pre-computed silhouette-signatures, modelled as a response surface of the area-of-silhouettes.