Abstract: An apparatus for processing media content includes at least one hardware processor coupled to at least one memory. The at least one memory stores instructions that when executed cause the at least one hardware processor to perform operations. The operations include generating three-dimensional (3D) representations of media elements present in one or more two-dimensional (2D) images representing a 2D scene with the media content. A 3D volume representation of the 2D scene is generated based on aggregating the 3D representations. A 3D void space associated with the 2D scene is segmented into a plurality of 3D void segments. The segmenting is based on the 3D volume representation. A 3D media element is inserted into at least one 3D void segment of the plurality of 3D void segments. The one or more 2D images are modified to include the at least one 3D void segment with the 3D media element.

Abstract: The disclosed embodiment generate a 3D representation of a 2D scene depicted to two dimensional video. The 3D representation includes individual 3D media elements representing objects included in the 2D scene. 3D void segments within the 2D scene are identified based on an aggregation of the individual 3D media elements. The 3D void segments are prioritized for insertion of additional 3D media elements within the 3D void spaces based on a variety of factors including lighting present at the 3D void segment, a distance of the 3D void segment from a center of the 2D scene, a size of the 3D void segment, and a time duration the 3D void segment is present in the 2D scene. A new 3D media element in these selected for insertion into the 2D scene based on the priorities of the 3D void segments.