System and a method for artificial neural-network based animation

A method of animating an image of an object, the method comprising:

• receiving at least one source image, depicting a first object and an input video, depicting movement of a second object;
• sampling the input video, to obtain a sampled image of the second object;
• analyzing the first image and the sampled image to obtain a transformation function, transferring at least one identity-invariant feature between the first object and the second object;
• applying the transformation function on the source image, to produce an output image depicting a third object, comprising at least one identity-invariant feature of the second object;
• repeating the steps of analyzing and applying, with a plurality of samples of the input video, to obtain a respective plurality of output images;
• and
• appending the plurality of output images to obtain an output video, depicting animation of the first object.

A system for animating an image of a face, the system comprising:

• a non-transitory memory device, wherein modules of instruction code are stored, and a processor associated with the memory device, and configured to execute the modules of instruction code, whereupon execution of said modules of instruction code, the processor is configured to:
• receive a first image, depicting a first face;
• sample an input video, depicting movement of a second face, to obtain at least one sampled image of the second face;
• analyze the first image and the at least one sampled image to obtain, for each image, at least one feature, selected from a list consisting of:
• a pose feature, and an expression feature;
• and
• based on the obtained features, generate an output video, depicting movement of the first face, that is substantially identical to movement of the second face and having the same expression as the second face.