A fully automatic model deformation propagation method and system
The invention relates to a fully automatic model deformation propagation method, comprising the following steps: obtaining a first deformation gradient vector and a second deformation gradient vectorof a first model base and a second model base respectively; Obtaining a first distribution vector of...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention relates to a fully automatic model deformation propagation method, comprising the following steps: obtaining a first deformation gradient vector and a second deformation gradient vectorof a first model base and a second model base respectively; Obtaining a first distribution vector of the first model library with the first deformation gradient vector and obtaining a second distribution vector of the second model library with the second deformation gradient vector; Obtaining a similarity of any pair of models between the first model base and the second model base; training a cycled generative adversarial network by using the first distribution vector, the second distribution vector, and the similarity training, and establishing a mapping network representing a mapping relationship between the first distribution vector and the second distribution vector; The first model specifies a specified deformation gradient vector of the deformation process, generates a specified distribution vector, maps the |
---|