Abstract: Methods and systems for compressing and decompressing vertex data in a triangular mesh may include identifying a first vertex to be decompressed and a plurality of previously decompressed neighboring vertices. A predicted position for the first vertex is determined as a function of adding a first edge vector and a second edge vector to a second vertex among the neighbors, wherein the second vertex is opposite the first vertex. For instance, the neighbors may be located on the perimeter of a hexagon with the first vertex. A received correction variable for the first vertex is then added to the predicted position to obtain the decompressed position of the first vertex. This prediction scheme provides more accurate vertex position predictions, thereby improving compression rates for three-dimensional geometric data. A corresponding method for compression may be used.

Abstract: A method including determining a mesh includes irregular connectivity, in response to determining the mesh includes irregular connectivity regularize the mesh and generate regularization data, and compressing the regularized mesh and the regularization data.

Abstract: A method including identifying a first vertex as a vertex to be compressed, identifying a plurality of neighboring vertices as compressed vertices, predicting a position of a second vertex, the second vertex being proximate to one of the plurality of neighboring vertices, predicting a position of a third vertex, the third vertex being proximate to the first vertex, generating a correction variable based on the position of the second vertex and a position of the one of the plurality of neighboring vertices, and determining a position of the first vertex based on the position of the third vertex and the correction variable.

Abstract: Techniques of compressing triangular mesh data involve generating a neighborhood table (i.e., a table) of fixed size that represents a neighborhood of a predicted vertex of a triangle within a triangular mesh for input into a machine-learning (ML) engine. For example, such a neighborhood table as input into a ML engine can output a prediction for a value (e.g., a position) of a vertex. The residual between the prediction and the actual value of the vertex is stored in an array. The data in the array representing the residuals may be compressed and transmitted over a network. Upon receipt by a computer, the array may be decompressed by the computer. Obtaining the actual value involves the receiving computer generating the same neighborhood table, inputting that neighborhood table into the same ML engine to produce the predicted value, and adding the predicted value to the residual from the decompressed file.

Abstract: Techniques of compressing triangular mesh data involve generating a neighborhood table (i.e., a table) of fixed size that represents a neighborhood of a predicted vertex of a triangle within a triangular mesh for input into a machine-learning (ML) engine. For example, such a neighborhood table as input into a ML engine can output a prediction for a value (e.g., a position) of a vertex. The residual between the prediction and the actual value of the vertex is stored in an array. The data in the array representing the residuals may be compressed and transmitted over a network. Upon receipt by a computer, the array may be decompressed by the computer. Obtaining the actual value involves the receiving computer generating the same neighborhood table, inputting that neighborhood table into the same ML engine to produce the predicted value, and adding the predicted value to the residual from the decompressed file.

Abstract: A method includes receiving geometric data to be encoded, generating a signature for the geometric data based on the at least one property associated with the geometric data, enumerating a first set of options, enumerating a second set of options, encoding the geometric data using the first option and the second option, decoding the encoded geometric data, determining a performance associated with encoding the geometric data, determining a performance associated with decoding the encoded geometric data, and training a regressor based on the signature, the enumerated first option, the enumerated second option, the performance associated with encoding the geometric data and the performance associated with decoding the encoded geometric data.