Abstract: Systems and methods are provided for interpolation of disparate inputs. A radial basis function neural network (RBFNN) may be used to interpolate the pose of a digital character. Input parameters to the RBFNN may be separated by data type (e.g. angular vs. linear) and manipulated within the RBFNN by distance functions specific to the data type (e.g. use an angular distance function for the angular input data). A weight may be applied to each distance to compensate for input data representing different variables (e.g. clavicle vs. shoulder). The output parameters of the RBFNN may be a set of independent values, which may be combined into combination values (e.g. representing x, y, z, w angular value in SO(3) space).

Abstract: Skinning parameters used to animate a virtual avatar can include mesh weights and joint transforms of a skeleton. Systems and methods are provided for determining skinning parameters using an optimization process subject to constraints based on human-understandable or anatomically-motivated relationships among skeletal joints. Input to the optimization process can include a high-order skeleton and the applied constraints can dynamically change during the optimization. The skinning parameters can be used in linear blend skinning (LBS) applications in augmented reality.

Abstract: Methods and systems for aligning head scans of a subject for a virtual avatar can be based on locating eyes of the subject in the scans. After one or more eyeball models are fitted to reference candidate points of a sclera of each eyeball of the subject in a reference head scan, an additional reference point can be inferred from the eyeball models. The eyeball models can be fitted to candidate points of the sclera of each eyeball of the subject in another head scan and an additional point can be inferred from the fitted eyeball models. An affine transformation can be determined between the head scans based on the eyeball models fitted to the candidate points in the reference head scan and the other head scan and the additional points inferred. The methods and systems can be used for rigging or animating the virtual avatar.