Abstract: Mechanisms for selecting formats for streaming media content items are provided.

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

Abstract: Systems and methods are disclosed for spherical three dimensional video rendering for virtual reality. A method includes receiving a spherical two-dimensional (2D) input image and a corresponding spherical depth map to be used in a creation of a spherical three-dimensional (3D) video, determining, by a processing device, a pixel shift value for each pixel of the spherical 2D input image based on the spherical depth map, and generating, based on the spherical 2D input image and the pixel shift values, a modified spherical image, wherein the modified spherical image in combination with the spherical 2d input image comprises at least one frame in the spherical 3D video.