Interactive augmented reality (AR) based video creation from existing video

A device for processing video content, the device comprising:

• a memory configured to store a set of frames having extracted one or more object clusters;
• and
• processing circuitry, coupled to the memory, and configured to:
• receive a set of frames having extracted one or more object clusters, wherein the one or more object clusters are extracted from a plurality of frames, wherein at least one of the one or more object clusters is an object cluster with movement through the plurality of frames;
• render one or more of the set of frames in a live camera feed of a device;
• generate information indicative of a position where a user is to be positioned in video content, that is subsequently generated, for interaction with the one or more object clusters, wherein the user is not interacting with the one or more object clusters in the received set of frames;
• and
• generate the video content based on the rendered one or more set of frames and the position where the user is to be positioned for interacting with the extracted one or more object clusters, wherein the generated video content includes both the extracted one or more object clusters and the user at the position.

A computer-readable storage medium storing instructions thereon that when executed cause one or more processors to:

• receive a set of frames having extracted one or more object clusters, wherein the one or more object clusters are extracted from a plurality of frames, wherein at least one of the one or more object clusters is an object cluster with movement through the plurality of frames;
• render one or more of the set of frames in a live camera feed of a device;
• generate information indicative of a position where a user is to be positioned in video content, that is subsequently generated, for interaction with the one or more object clusters, wherein the user is not interacting with the one or more object clusters in the received set of frames;
• and
• generate the video content based on the rendered one or more set of frames and the position where the user is to be positioned for interacting with the extracted one or more object clusters, wherein the generated video content includes both the extracted one or more object clusters and the user at the position.