No-reference video quality metrics

Image for no reference metrics

No-reference video quality metrics are algorithms which measure the quality of a video by measuring, from the video under test, the distortions that may have been caused by encoding, transcoding and/or transmission.

Usually, a no-reference metric explores the video frames at pixel level in order to detect and measure the distortions which may have been generated. It implies to know the types of possible distortions. And different video codecs produce different distortions.

Therefore, a no-reference metric is always dedicated to a particular encoding format.

AccepTV has developped no-reference metrics for the most used encoding formats: HEVC (H.265), MPEG-4/AVC (H.264) and MPEG-2.

Each video quality metric is dedicated to a given encoding format.

For each codec, the corresponding metric measures the distortions generated by the encoding:

  • No-Reference metric for HEVC (H.265) video: measurement of blur perception, measurement of picture flatness.
  • No-Reference metric for MPEG-4/AVC (H.264) video: measurement of blockiness visibility, measurement of blur perception, measurement of contrast between macroblocs (because of the deblocking filter).
  • No-Reference metric for MPEG-2 video: measurement of blockiness visibility, measurement of blur perception.

This is essential and makes a great difference with some other existing video quality measurement solutions. Indeed, some of these solutions are designed using one given encoding format, then vendors claim that they work for any format. For example, many solutions are designed for MPEG-2 because they measure the visibility of MPEG-2 artefacts like blockiness and blur (please note that measuring blockiness on MPEG-2 is quite easy since all the blocks have the same size). And yet, these solutions are also proposed to measure the quality of videos that have been encoded using H.264 (MPEG-4/AVC). However:

  • the main distortion in H.264 encoded videos is not blockiness but is more contrast loss (so the importance given to the different distortions types has to be adapted to each format).
  • the H.264 decoder contains a deblocking filter (so the main cause of blockiness is packets loss)
  • using H.264 encoding, the blocks have various sizes (so blockiness measurement has to be adapted to H.264)
  • with HEVC, blockiness is nearly inexistent and the distortions mainly result in blur and picture flatness

Therefore, you must understand that a video quality metric designed for MPEG-2 must not be used to measure the quality of videos encoded with H.264 (or even worse: with HEVC).

Related products (evaluations are free):