Efficient pose deformations for human models in customized sizes and shapes

Modelling dynamic pose deformations of human subjects is an important topic in many research applications. Existing approaches of human pose deformations can be classified as volume-based, skeletal animation and example-based methods. These approaches have both strengths and limitations. However, for models in customized shapes, it is very challenging to deform these models into different poses rapidly and realistically. We propose a conceptual model to realize rapid and realistic pose deformation to customized human models by the integration of skeletal-driven rigid deformation and example-learnt non-rigid surface deformation. Based on this framework, a method for rapid automatic pose deformation is developed to deform human models of various body shapes into a series of dynamic poses. A series of algorithms are proposed to complete the pose deformation automatically and efficiently, including automatic segmentation of body parts and skeleton embedding, skeletal-driven rigid deformation, training of non-rigid deformation from pose dataset; shape mapping of non-rigid deformation, and integration of rigid and non-rigid deformations. Experiment has shown that the proposed method can customize accurate human models based on two orthogonal-view photos and also efficiently generate realistic pose deformations for the customized models.