Method for creating a variable model of a face of a person
A method for creating a variable model of a face of a person, the method comprises: obtaining a non-riggable model of the face of the person; performing a first approximation process that comprises generating an intermediate variable model that approximates the non-riggable model, using an interactive variable model infrastructure; wherein the generating comprises iteratively changing shape parameters of the intermediate model until fulfilling a proximity condition; and performing a second approximation process that comprises generating the variable model, by iteratively modifying vertices.
1. A method for creating a variable model of a face of a person, the method comprises:
obtaining a non-riggable model of the face of the person;
performing a first approximation process that comprises generating an intermediate variable model that approximates the non-riggable model, using an interactive variable model infrastructure; wherein the generating comprises iteratively changing shape parameters of the intermediate model until fulfilling a gradual descent proximity condition;
obtaining expression parameters regarding a current expression of the person, and modifying, using the interactive variable model infrastructure, the variable model based on the expression parameters; and
performing a second approximation process that comprises generating the variable model, by iteratively modifying vertices.
2. The method according to claim 1 , wherein a number of shape parameters is a fraction of a number of the vertices.
3. The method according to claim 2 , wherein the variable model is a Flame model.
4. The method according to claim 1 , wherein a number of the shape parameters does not exceed 100.
5. The method according to claim 1 , wherein the non-riggable model lacks an interactive variable model infrastructure.
6. A non-transitory computer readable medium for creating a variable model of a face of a person, the non-transitory computer readable medium stores instructions that once executed by a processor cause the processor to execute steps, the steps comprising:
obtaining a non-riggable model of the face of the person;
performing a first approximation process that comprises generating an intermediate variable model that approximates the non-riggable model, using an interactive variable model infrastructure; wherein the generating comprises iteratively changing shape parameters of the intermediate model until fulfilling a gradual descent proximity condition;
obtaining expression parameters regarding a current expression of the person, and modifying, using the interactive variable model infrastructure, the variable model based on the expression parameters; and
performing a second approximation process that comprises generating the variable model, by iteratively modifying vertices.
7. The non-transitory computer readable medium according to claim 6 , wherein a number of shape parameters is a fraction of a number of the vertices.
8. The non-transitory computer readable medium according to claim 7 , wherein the variable model is a Flame model.
9. The non-transitory computer readable medium according to claim 6 , wherein a number of the shape parameters does not exceed 100.
10. The non-transitory computer readable medium according to claim 6 , wherein the non-riggable model lacks an interactive variable model infrastructure.