Machine learning techniques for increasing color consistency across videos

Abstract

Disclosed systems and methods use machine-learning techniques to determine a set of parameters that if applied to a target video, apply a color characteristic of a reference video to the target video. For example, a color consistency application executing on a computing device computes a feature vector including a representation of a reference video and a target video. The application determines a set of color parameters (e.g., exposure, color temperature, tint, etc.) by applying the feature vector to one or more predictive models trained to determine color consistency. The application generates a preview image by applying the parameters to the target video. The applying causes an adjustment of exposure, color temperature, or tint in the target video such that a color consistency of the adjusted target video is consistent with a color consistency of the reference video. The color consistency application provides settings to further adjust the parameters.