Techniques for predicting perceptual video quality based on complementary perceptual quality models

摘要

In various embodiments, the ensemble prediction application calculates a quality score for reconstructed visual content derived from the visual content. The ensemble prediction application calculates a first quality score for the reconstructed video content based on a first set of values for the first set of features and a first model associating the first set of values with a first quality score. . The ensemble prediction application calculates a second quality score for the reconstructed video content based on a second set of values for the second set of features and a second model associating the second set of values with a second quality score. . The ensemble prediction application then determines an overall quality score for the reconstructed video content based on the first quality score and the second quality score. The overall quality score indicates the level of visual quality associated with the streamed video content.