3D model shape transformation method and apparatus

摘要

Disclosed herein is a 3D model shape transformation apparatus. The 3D model shape transformation apparatus includes a camera unit, a shape restoration unit, a skeleton structure generation unit, and a skeleton transformation unit. The camera unit obtains a plurality of 2D images in a single frame by capturing the shape of an object. The shape restoration unit generates a 3D volume model by restoring the shape of the object based on the plurality of 2D images. The skeleton structure generation unit generates the skeleton structure of the 3D volume model. The skeleton transformation unit transforms the size and posture of the 3D volume model into those of a template model by matching the skeleton structure of the template model with the skeleton structure of the 3D volume model.

主权项

1. A 3-dimensional (3D) model shape transformation method, comprising:
generating a volume model, in which a shape of an object is restored, based on a plurality of 2D images of the object; generating a skeleton structure of the volume model using boundary points between portions of a body of the volume model; generating a skeleton transformation model by transforming a skeleton structure of a template model into the skeleton structure of the volume model in order to match a size and a posture of the template model with a size and a posture of the volume model; generating a shape transformation model corresponding to the shape of the object by transforming appearance of the skeleton transformation model based on cross-sections of the volume model in order to match appearance of the skeleton transformation model with appearance of the volume model; and generating the template model before generating the volume model, wherein the generating the template model comprises:
generating a 3D skeleton model by forming a skeleton structure of a 3D mesh model; andgenerating the template model by transforming appearance of the 3D skeleton model based on each of relevant Non-Uniform Rational B-Spline (NURBS) surfaces,wherein the generating the template model by transforming the appearance of the 3D skeleton model comprises:
extracting a cross-section of a predetermined location of the 3D skeleton model; andgenerating the NURBS surface by performing interpolation on the cross-section of a predetermined location of the 3D skeleton model, wherein the generating the shape transformation model comprises generating the shape transformation model by matching a cross-section of a predetermined location of the skeleton transformation model with a cross-section of the volume model.