Abstract: A technique is described herein for adding a digital watermark to a mesh. The mesh describes a three-dimensional object using a plurality of vertices and edges, which together define a plurality of polygonal shapes (e.g., triangles). The technique involves identifying at least one anomalous element of the mesh. The technique then supplements one or more of the anomalous elements by adding a computer-readable code to the anomalous element(s). That computer-readable code includes a digital watermark. An anomalous element corresponds to a part of the mesh that qualifies as a statistically atypical occurrence within the mesh, based on a specified rule that defines what constitutes a statistically atypical occurrence. In a reading stage, the technique finds the anomalous element(s). It then reads the digital watermark that has been encoded into the anomalous element(s).

Abstract: A technique is described herein for adding a digital watermark to a mesh. The mesh describes a three-dimensional object using a plurality of vertices and edges, which together define a plurality of polygonal shapes (e.g., triangles). The technique involves identifying at least one anomalous element of the mesh. The technique then supplements one or more of the anomalous elements by adding a computer-readable code to the anomalous element(s). That computer-readable code includes a digital watermark. An anomalous element corresponds to a part of the mesh that qualifies as a statistically atypical occurrence within the mesh, based on a specified rule that defines what constitutes a statistically atypical occurrence. In a reading stage, the technique finds the anomalous element(s). It then reads the digital watermark that has been encoded into the anomalous element(s).

Abstract: A system for training a neural network generates a plurality of training meshes based on an input mesh. The plurality of training meshes include at least one mesh perceptually similar to the input mesh and one arbitrarily selected mesh perceptually dissimilar to the input mesh. The neural network is trained using the input mesh and the plurality of training meshes by tuning output of the neural network to identify similar non-identical meshes. The trained neural network is robust in identifying meshes similar to an unknown mesh input to the trained neural network.

Abstract: The present invention relates to a method for the creation of large hierarchical computer graphics datasets. The method comprises combination (401) of one or more primitive computer graphics data objects (400) into larger data objects, and simplifying each of the said combined data objects (402). The simplified objects are then reused (405) in further combination steps in order to increasingly create higher order objects. The created hierarchical computer graphics data set is inherently optimized for fast rendering, and a method of rendering such data is also described.

Abstract: The present invention relates to a method for the creation of large hierarchical computer graphics datasets. The method comprises combination (401) of one or more primitive computer graphics data objects (400) into larger data objects, and simplifying each of the said combined data objects (402). The simplified objects are then reused (405) in further combination steps in order to increasingly create higher order objects. The created hierarchical computer graphics data set is inherently optimized for fast rendering, and a method of rendering such data is also described.