Image-Based Object Editing

Abstract  We examine the problem of editing complex 3D objects. We convert the problem of editing a 3D object of arbitrary size and surface properties to a problem of editing a 2D image. We allow the user to specify edits in both geometry and surface properties from any view and at any resolution they find convenient, regardless of the interactive rendering capability of their computer. We use specially-constrained shape from shading algorithms to convert a shaded image specified by the user into a 3D geometry.