Abstract: An animation generation method for tracking a facial expression and a neural network training method thereof are provided. The animation generation method for tracking a facial expression includes: driving a first role model according to an expression parameter set to obtain a virtual expression image corresponding to the expression parameter set; applying a plurality of real facial images to the virtual expression image corresponding to the facial expression respectively to generate a plurality of real expression images; training a tracking neural network according to the expression parameter set and the real expression images; inputting a target facial image to the trained tracking neural network to obtain a predicted expression parameter set; and using the predicted expression parameter set to control a second role model.

Abstract: An animation generation method for tracking a facial expression and a neural network training method thereof are provided. The animation generation method for tracking a facial expression includes: driving a first role model according to an expression parameter set to obtain a virtual expression image corresponding to the expression parameter set; applying a plurality of real facial images to the virtual expression image corresponding to the facial expression respectively to generate a plurality of real expression images; training a tracking neural network according to the expression parameter set and the real expression images; inputting a target facial image to the trained tracking neural network to obtain a predicted expression parameter set; and using the predicted expression parameter set to control a second role model.

Abstract: A shape-sensing system includes a deformable object, a strip substrate, and a plurality of bend sensors. The deformable object is configured to deform when a first force is exerted on the deformable object. The strip substrate is installed in the shape-sensing system such that the strip substrate deforms in response to deformation of the deformable object. The plurality of bend sensors is fixedly attached to a surface of the strip substrate at different respective locations for generating respective values in response to deformation of the strip substrate. The respective values are used for obtaining tracked deformation of the deformable object.