초록 ▼

A three-dimensional model of an object can be generated using a computer system by identifying reference points in two or more 2D representations of the object to be modeled, and deriving 3D positional data based on an application of an initial estimation model to the identified reference points. A

A three-dimensional model of an object can be generated using a computer system by identifying reference points in two or more 2D representations of the object to be modeled, and deriving 3D positional data based on an application of an initial estimation model to the identified reference points. A texture-mapped version of the 3D model can be generated by mapping texture information from the 2D representations onto the derived 3D positional data.

대표청구항 ▼

1. A computer-implemented method for generating 3D image data descriptive of an object, the method comprising:receiving 2D image data for at least two input images of an object, each input image representing a different viewpoint of the object; determining 2D position data for reference points of th

1. A computer-implemented method for generating 3D image data descriptive of an object, the method comprising:receiving 2D image data for at least two input images of an object, each input image representing a different viewpoint of the object; determining 2D position data for reference points of the object from the 2D image data, each of the reference points being included in at least two of the input images; if camera parameters for the input images are not known, deriving (i) camera parameters for each of the input images, and (ii) 3D position data for the reference points, based on the 2D position data for the reference points of the input images; and creating a 3D texture-mapped model of the object by texture mapping from the 2D image data for the input images using the camera parameters for the input images and the 3D position data for reference points of the object; wherein deriving 3D image data comprises: using a reference model for the object providing 3D position data for points of the object, including control points corresponding to the reference points of the object and non-control points, wherein each non-control point has a known relation to surrounding control points; repositioning the control points of the reference model based on the 3D position data determined for the reference points of the object; and repositioning non-control points of the reference model based on the repositioned control points and the known relation of the non-control points to the surrounding control points, wherein the texture mapping from the 2D image data for the input images further uses the derived 3D position data for the non-control points of the reference model.