According to one implementation, a system for differentially transforming video content includes a computing platform having a hardware processor and a system memory storing a video reformatting software code. The hardware processor executes the video reformatting software code to receive an input video file including video content formatted for a first set of coordinates, and to detect one or more principle features depicted in the video content based on a predetermined principle feature identification data corresponding to the video content. The hardware processor further executes the video reformatting software code to differentially map the video content to a second set of coordinates to produce a reformatted video content. The resolution of the one or more principle features is enhanced relative to other features depicted in the reformatted video content.
BACKGROUND(1) Video content may be reformatted and/or compressed in a variety of ways. For example, spherical video is often represented as a projection onto rectangular frames. A commonly used projection technique for spherical video is referred to as equirectangular projection or latitude/longitude projection. According to that approach, each pixel within the rectangular frame represents a latitudinal and longitudinal coordinate from the projected sphere. In addition, a linear scaling is typically used for both the latitudinal and longitudinal coordinates, which results in features shown in the northernmost and southernmost latitudes of a spherical video frame being disproportionately emphasized in the corresponding rectangular frame.SUMMARY(2) There are provided systems and methods for differentially transforming video, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.
1. A system for differentially transforming video content, the system comprising: a computing platform including a hardware processor and a system memory; a video reformatting software code stored in the system memory; the hardware processor configured to execute the video reformatting software code to: receive an input video file including a spherical video content formatted for a plurality of latitudinal and longitudinal spherical coordinates; detect at least one principle feature depicted in the spherical video content based on a predetermined principle feature identification data corresponding to the spherical video content; and differentially map the spherical video content formatted for the plurality of latitudinal and longitudinal spherical coordinates to a plurality of Cartesian coordinates to produce a reformatted video content having a lower resolution relative to the spherical video content; wherein the differentially mapping of the spherical video content formatted for the plurality of latitudinal and longitudinal spherical coordinates to the plurality of Cartesian coordinates emphasizes the at least one detected principle feature in the reformatted video content by having the at least one detected principle feature be at a higher resolution relative to a plurality of non-principle features in the reformatted video content while the reformatted video content has the lower resolution relative to the spherical video content.
8. A method for use by a system including a computing platform having a hardware processor and a system memory storing a video reformatting software code, the method comprising: receiving, using the hardware processor, an input video file including a spherical video content formatted for a plurality of latitudinal and longitudinal spherical coordinates; detecting, using the hardware processor, at least one principle feature depicted in the spherical video content based on a predetermined principle feature identification data corresponding to the spherical video content; and differentially mapping the spherical video content formatted for the plurality of latitudinal and longitudinal spherical coordinates to a plurality of Cartesian coordinates to produce a reformatted video content having a lower resolution relative to the spherical video content; wherein the differentially mapping of the spherical video content formatted for the plurality of latitudinal and longitudinal spherical coordinates to the plurality of Cartesian coordinates emphasizes the at least one detected principle feature in the reformatted video content by having the at least one detected principle feature be at a higher resolution relative to a plurality of non-principle features in the reformatted video content while the reformatted video content has the lower resolution relative to the spherical video content.