Generation and quality improvement of 3D models from silhouettes of 2D images

Abstract

The shape-from-silhouette (SFS) method has been widely used in 3D shape reconstruction. It uses silhouettes of a series of 2D images captured from multiple viewpoints of an object to generate a 3D model that describes the visual hull of the object. The SFS method faces an inherent problem that virtual features appear all over the model. In addition, concavities on the object may wrongly be modeled as convex shapes because they are invisible on image silhouettes. The purpose of this study is to propose a method to generate a 3D model from silhouettes of multiple images and propose a quality improvement method to overcome the above-mentioned problems. The 3D modeling method focuses on accurate evaluation of 3D points intersected by all polyhedra from different views and the removal of poor meshes on triangulation. The quality improvement method is essentially an iterative procedure, which for smoothing the model and eliminating virtual features and artifacts, while preserving the consistency of all silhouettes. The proposed method is to be used for product presentations in e-commerce, in which the 3D model must be covered with color texture of an object. Several examples are presented to illustrate the capability of the proposed method.