Abstract

We propose a method to estimate the detailed 3D shape of a person from images of that person wearing clothing. The approach ex- ploits a model of human body shapes that is learned from a database of over 2000 range scans. We show that the parameters of this shape model can be recovered independently of body pose. We further propose a generalization of the visual hull to account for the fact that observed silhouettes of clothed people do not provide a tight bound on the true 3D shape. With clothed sub jects, different poses provide different con- straints on the possible underlying 3D body shape. We consequently combine constraints across pose to more accurately estimate 3D body shape in the presence of occluding clothing. Finally we use the recovered 3D shape to estimate the gender of sub jects and then employ gender- specific body models to refine our shape estimates. Results on a novel database of thousands of images of clothed and “naked” sub jects, as well as sequences from the HumanEva dataset, suggest the method may be accurate enough for biometric shape analysis in video.