Method and system for image processing

A computer implemented method for automatic interpolation or extrapolation of visual modifications from a set of one or more keyframes extracted from a set of one or more target video frames, the method comprising:

• instantiating a machine learning model architecture;
• receiving the set of one or more keyframes;
• providing the set of one or more keyframes for visual modification;
• receiving a set of one or more modified keyframes;
• training the machine learning model architecture using the set of one or more modified keyframes and the set of one or more keyframes, the machine learning model architecture to obtain a trained machine learning model architecture configured for transferring the visual modification to other video frames;
• and
• generating a corresponding set of one or more modified target video frames having the automatically interpolated or extrapolated visual modifications.

A non-transitory computer readable medium, storing machine-interpretable instruction sets which when executed by a processor, cause the processor to perform a method for automatic interpolation or extrapolation of visual modifications from a set of one or more keyframes extracted from a set of one or more target video frames, the method comprising:

• instantiating a machine learning model architecture;
• receiving the set of one or more keyframes;
• providing the set of one or more keyframes for visual modification;
• receiving a set of one or more modified keyframes;
• training the machine learning model architecture using the set of one or more modified keyframes and the set of one or more keyframes, the machine learning model architecture to obtain a trained machine learning model architecture;
• and
• processing one or more frames of the set of one or more target video frames to generate a corresponding set of one or more modified target video frames having the automatically interpolated or extrapolated visual modifications.