Abstract: High-level geometry processing has been a hot topic in graphics community. The functionality analysis of 3D models is an essential issue in this area. Existing 3D models often exhibit both large intra-class and inter-class variations in shape geometry and topology, making the consistent analysis of functionality challenging. Traditional 3D shape analysis methods which rely on geometric shape descriptors can not obtain satisfying results on these 3D models. We develop a new 3D shape descriptor based on the interactions between 3D models and virtual human actions, which is called Action-Based 3D Descriptor (AB3D). Due to the implied semantic meanings of virtual human actions, we obtain encouraging results on consistent segmentation based on AB3D. Finally, we present a method for recognition and reconstruction of scanned 3D indoor scenes using our AB3D. Experiments show that AB3D is a promising shape descriptor toward functionality analysis of 3D shapes.