Rapid 3D modelling from live video

Off-line model reconstruction relies on an image collection phase and a slow reconstruction phase, requiring a long time to verify a model obtained from an image sequence is acceptable. Our reconstruction system, ProFORMA, generates 3D models on-line as the input sequence is being collected. As the user rotates the object in front of a stationary camera, generated partial models aid view planning and are also used by the system to robustly track the pose of the object. Models are rapidly produced through a Delaunay tetra-hedralisation of points obtained from on-line structure from motion estimation, followed by a probabilistic tetrahedron carving step to obtain a textured surface mesh of the object.