A two-dimensional image is transformed into at least one portion of a human or animal body into a three-dimensional model. An image is acquired that includes the at least one portion of the human or animal body. An identification is made of the at least one portion within the image. Searches are made for features indicative of the at least one portion of the human or animal body within the at least one portion. One or more identifications are made of a set of landmarks corresponding to the features. An alignment is a deformable mask including the set of landmarks. The deformable mask includes a number of meshes corresponding to the at least one portion of the human or animal body. The 3D model is animated by dividing it into concentric rings, quasi rings and applying different degrees of rotation to each ring.

Present application refers to a method, a model generation unit and a computer program (product) for generating trained models (M) of moving persons, based on physically measured person scan data (S). The approach is based on a common template (T) for the respective person and on the measured person scan data (S) in different shapes and different poses. Scan data are measured with a 3D laser scanner. A generic personal model is used for co-registering a set of person scan data (S) aligning the template (T) to the set of person scans (S) while simultaneously training the generic personal model to become a trained person model (M) by constraining the generic person model to be scan-specific, person-specific and pose-specific and providing the trained model (M), based on the co-registering of the measured object scan data (S).

A two-dimensional image is transformed into at least one portion of a human or animal body into a three-dimensional model. An image is acquired that includes the at least one portion of the human or animal body. An identification is made of the at least one portion within the image. Searches are made for features indicative of the at least one portion of the human or animal body within the at least one portion. One or more identifications are made of a set of landmarks corresponding to the features. An alignment is a deformable mask including the set of landmarks. The deformable mask includes a number of meshes corresponding to the at least one portion of the human or animal body. The 3D model is animated by dividing it into concentric rings, quasi rings and applying different degrees of rotation to each ring.

A two-dimensional image is transformed into at least one portion of a human or animal body into a three-dimensional model. An image is acquired that includes the at least one portion of the human or animal body. An identification is made of the at least one portion within the image. Searches are made for features indicative of the at least one portion of the human or animal body within the at least one portion. One or more identifications are made of a set of landmarks corresponding to the features. An alignment is a deformable mask including the set of landmarks. The deformable mask includes a number of meshes corresponding to the at least one portion of the human or animal body. The 3D model is animated by dividing it into concentric rings, quasi rings and applying different degrees of rotation to each ring.

A two-dimensional image is transformed into at least one portion of a human or animal body into a three-dimensional model. An image is acquired that includes the at least one portion of the human or animal body. An identification is made of the at least one portion within the image. Searches are made for features indicative of the at least one portion of the human or animal body within the at least one portion. One or more identifications are made of a set of landmarks corresponding to the features. An alignment is a deformable mask including the set of landmarks. The deformable mask includes a number of meshes corresponding to the at least one portion of the human or animal body. The 3D model is animated by dividing it into concentric rings, quasi rings and applying different degrees of rotation to each ring.

A computing system is presented including a processor and non-transient memory which includes instructions to execute a method including receiving a motion instruction message which includes graphical objects to be modified and instructions to be assigned to each of the graphical objects to be modified, where an instruction includes a property to be applied to a graphical object. The method also includes identifying actors to be assigned to each of the graphical objects based on the instructions assigned to each of the graphical objects, where an actor is a non-graphical object capable of executing one or more instructions. The method also includes generating the actors for each of the graphical objects, executing the instructions assigned to each of the graphical objects via the actors, and outputting the modified graphical objects for display.

A stylesheet data structure includes a plurality of stylesheet records, each comprising an ontology concept field, a presentation instruction field, and a presentation identifier field. Techniques for ontology driven animation includes receiving a request to render an instance of a first concept in an annotation with an associated ontology. It is determined whether a stylesheet file includes a first stylesheet record that indicates the first concept, wherein the first stylesheet record also indicates a first presentation identifier. If so, then an instance of a first component of the first concept is rendered according to a presentation instruction indicated in a second stylesheet record that also indicates the first presentation identifier. In some embodiments, the instance of the first component of the first concept is an instance of the first concept and the second stylesheet record is the first stylesheet record.

System, method and apparatuses of the present invention directed to a paradigm of manuscript generation and manipulation from a source textual document, involving a first format, into another document in a second format. A converter converts scenes, dialog, milieus, movements, actions and other instructions input or stored in a first format into a second, different format, and vice versa.

A novel and useful mechanism for the skinning of 3D meshes with reference to a skeleton utilizing statistical weight optimization techniques. The mechanism of the present invention comprises (1) an efficient high quality linear blend skinning (LBS) technique based on a set of skeleton deformations sampled from the manipulation space; (2) a joint placement algorithm to optimize the input skeleton; and (3) a set of tools for a user to interactively control the skinning process. Statistical skinning weight maps are computed using an as-rigid-as-possible (ARAP) optimization. The method operates with a coarsely placed initial skeleton and optimizes joint placements to improve the skeleton's alignment. Bones may also be parameterized incorporating twists, bends, stretches and spines. Several easy to use tools add additional constraints to resolve ambiguous situations when needed and interactive feedback is provided to aid users. Quality weight maps are generated for challenging deformations and various data types (e.g., triangle, tetrahedral meshes), including noisy, complex and topologically challenging examples (e.g., missing triangles, open boundaries, self-intersections, or wire edges).

Present application refers to a method, a model generation unit and a computer program (product) for generating trained models (M) of moving persons, based on physically measured person scan data (S). The approach is based on a common template (T) for the respective person and on the measured person scan data (S) in different shapes and different poses. Scan data are measured with a 3D laser scanner. A generic personal model is used for co-registering a set of person scan data (S) aligning the template (T) to the set of person scans (S) while simultaneously training the generic personal model to become a trained person model (M) by constraining the generic person model to be scan-specific, person-specific and pose-specific and providing the trained model (M), based on the co registering of the measured object scan data (S).