Systems for generating digital objects to animate sketches

A system comprising:

• a memory component;
• and
• a processing device coupled to the memory component, the processing device to perform operations comprising:
• receiving input data describing a user sketched digital object having a pose and a user defined non-photorealistic style;
• generating a latent vector representation of the user defined non-photorealistic style using an encoder of a generative adversarial network that is trained on training data to receive a first digital object having a first pose and a first non-photorealistic style and a second digital object having a second pose and a second non-photorealistic style as an input and generate a new digital object having the first pose and the second non-photorealistic style as an output;
• generating a digital object having the pose and a non-photorealistic style using a generator of the generative adversarial network based on the latent vector representation of the user defined non-photorealistic style;
• and
• modifying the latent vector representation of the user defined non-photorealistic style based on a comparison between the user defined non-photorealistic style and the non-photorealistic style.

A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, causes the processing computing device to perform operations comprising:

• receiving input data describing a user sketched digital object having a pose and a user defined non-photorealistic style;
• generating a latent vector representation of the user defined non-photorealistic style using an encoder of a generative adversarial network that is trained on training data to receive a first digital object having a first pose and a first non-photorealistic style and a second digital object having a second pose and a second non-photorealistic style as an input and generate a new digital object having the first pose and the second non-photorealistic style as an output;
• generating a digital object having the pose and a non-photorealistic style using a generator of the generative adversarial network based on the latent vector representation of the user defined non-photorealistic style;
• and
• modifying the latent vector representation of the user defined non-photorealistic style based on a comparison between the user defined non-photorealistic style and the non-photorealistic style.