Systems and methods for message embedding in three-dimensional image data

A computer-implemented method for watermark-based message embedding for three-dimensional images, the method comprising:

• obtaining, by one or more computing devices, three-dimensional image data and a message vector;
• inputting, by the one or more computing devices, the three-dimensional image data and the message vector into a machine-learned message embedding model;
• receiving, by the one or more computing devices from the machine-learned message embedding model, encoded three-dimensional image data comprising an embedded message based on the message vector;
• using, by the one or more computing devices, a machine-learned message extraction model to extract the embedded message from the encoded three-dimensional image data to obtain a reconstructed message vector;
• evaluating, by the one or more computing devices, a loss function that evaluates a reconstruction error that is associated with a difference between the message vector and the reconstructed message vector that is based on embedding the message vector and extracting the reconstructed message vector from the three-dimensional image data, wherein the loss function further evaluates a perceptual difference between the three-dimensional image data and the encoded three-dimensional image data that corresponds to the embedding of the embedded message;
• and
• modifying, by the one or more computing devices, values for one or more parameters of at least the machine-learned message embedding model based on the loss function.

One or more tangible, non-transitory computer readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:

• obtaining three-dimensional image data and a message vector;
• inputting the three-dimensional image data and the message vector into a machine-learned message embedding model;
• receiving, from the machine-learned message embedding model, encoded three-dimensional image data comprising an embedded message based on the message vector;
• using a machine-learned message extraction model to extract the embedded message from the encoded three-dimensional image data to obtain a reconstructed message vector;
• evaluating a loss function that evaluates a reconstruction error that is associated with a difference between the message vector and the reconstructed message vector that is based on embedding the message vector and extracting the reconstructed message vector from the three-dimensional image data, wherein the loss function further evaluates a perceptual difference between the three-dimensional image data and the encoded three-dimensional image data that corresponds to the embedding of the embedded message;
• and
• modifying values for one or more parameters of at least the machine-learned message embedding model based on the loss function.