Source-consistent techniques for predicting absolute perceptual video quality

Patent metadata

Field	Value
Publication number	US-11503304-B2
Application number	US-202017093456-A
Country	US
Kind code	B2
Filing date	Nov 9, 2020
Priority date	Dec 12, 2016
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

In various embodiments, a perceptual quality application computes an absolute quality score for encoded video content. In operation, the perceptual quality application selects a model based on the spatial resolution of the video content from which the encoded video content is derived. The model associates a set of objective values for a set of objective quality metrics with an absolute quality score. The perceptual quality application determines a set of target objective values for the objective quality metrics based on the encoded video content. Subsequently, the perceptual quality application computes the absolute quality score for the encoded video content based on the selected model and the set of target objective values. Because the absolute quality score is independent of the quality of the video content, the absolute quality score accurately reflects the perceived quality of a wide range of encoded video content when decoded and viewed.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving encoded video content from a server machine, wherein the encoded video content is derived from source video content;
performing at least one decoding operation on the encoded video content to generate re-constructed video content, wherein the re-constructed video content is associated with an absolute quality score that is computed by converting a base quality score associated with viewing the re-constructed video content on a base viewing device and reflects a spatial resolution of the source video content; and
displaying at least one frame of the re-constructed video content.

2. The computer-implemented method of claim 1 , further comprising receiving, from the server machine, second encoded video content that is associated with a second absolute quality score that reflects a second spatial resolution; and
aggregating the absolute quality score and the second absolute quality score to evaluate perceived video quality of media content streamed during a streaming session.

3. The computer-implemented method of claim 1 , wherein the absolute quality score predicts a perceived visual quality of the re-constructed video content when viewed on a first type of viewing device.

4. The computer-implemented method of claim 1 , further comprising receiving, from the server machine, second encoded video content that is derived from second source video content; and performing at least one decoding operation on the second encoded video content to generated second re-constructed video content that is associated with a second absolute quality score that reflects a second spatial resolution of the second source video content.

5. The computer-implemented method of claim 1 , further comprising computing the absolute quality score based on a model that is associated with the spatial resolution of the source video content.

6. The computer-implemented method of claim 1 , further comprising computing the absolute quality score based on a model that associates a set of objective values for a set of objective quality metrics with a given absolute quality score.

7. The computer-implemented method of claim 6 , wherein the set of objective quality metrics includes at least one of temporal information, a detail loss measure, or a visual information fidelity.

8. The computer-implemented method of claim 1 , further comprising selecting a model from a plurality of models based on the spatial resolution of the source video content, wherein each model included in the plurality of models is associated with a different spatial resolution; and computing the absolute quality score based on the model.

9. The computer-implemented method of claim 1 , wherein the absolute quality score reflects human-observed visual quality scores for re-constructed training video content.

10. One or more non-transitory computer-readable media including instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
receiving encoded video content from a server machine, wherein the encoded video content is derived from source video content;
performing at least one decoding operation on the encoded video content to generate re-constructed video content, wherein the re-constructed video content is associated with an absolute quality score that is computed by converting a base quality score associated with viewing the re-constructed video content on a base viewing device and reflects a spatial resolution of the source video content; and
displaying at least one frame of the re-constructed video content.

11. The one or more non-transitory computer-readable media of claim 10 , further comprising receiving, from the server machine, second encoded video content that is associated with a second absolute quality score that reflects a second spatial resolution; and aggregating the absolute quality score and the second absolute quality score to evaluate perceived video quality of media content streamed during a streaming session.

12. The one or more non-transitory computer-readable media of claim 10 , wherein the absolute quality score predicts a perceived visual quality of the re-constructed video content when viewed on a first type of viewing device.

13. The one or more non-transitory computer-readable media of claim 10 , further comprising receiving, from the server machine, second encoded video content that is derived from second source video content; and performing at least one decoding operation on the second encoded video content to generated second re-constructed video content that is associated with a second absolute quality score that reflects a second spatial resolution of the second source video content.

14. The one or more non-transitory computer-readable media of claim 10 , further comprising computing the absolute quality score based on a model that is associated with the spatial resolution of the source video content.

15. The one or more non-transitory computer-readable media of claim 10 , further comprising computing the absolute quality score based on a model that associates a set of objective values for a set of objective quality metrics with a given absolute quality score.

16. The one or more non-transitory computer-readable media of claim 15 , wherein the set of objective quality metrics includes at least one of temporal information, a detail loss measure, or a visual information fidelity.

17. The one or more non-transitory computer-readable media of claim 10 , further comprising selecting a model from a plurality of models based on the spatial resolution of the source video content, wherein each model included in the plurality of models is associated with a different spatial resolution; and computing the absolute quality score based on the model.

18. The one or more non-transitory computer-readable media of claim 10 , wherein the absolute quality score reflects human-observed visual quality scores for re-constructed training video content.

19. A system, comprising:
one or more memories storing instructions; and
one or more processors that are coupled to the one or more memories and, when executing the instructions, are configured to perform the steps of:
receiving encoded video content from a server machine, wherein the encoded video content is derived from source video content,
performing at least one decoding operation on the encoded video content to generate re-constructed video content, wherein the re-constructed video content is associated with an absolute quality score that is computed by converting a base quality score associated with viewing the re-constructed video content on a base viewing device and reflects a spatial resolution of the source video content, and
displaying at least one frame of the re-constructed video content.

20. The system of claim 19 , wherein the one or more processors are further configured to receive, from the server machine, second encoded video content that is associated with a second absolute quality score that reflects a second spatial resolution; and aggregate the absolute quality score and the second absolute quality score to evaluate perceived video quality of media content streamed during a streaming session.

21. The system of claim 19 , wherein the absolute quality score predicts a perceived visual quality of the re-constructed video content when viewed on a first type of viewing device.

22. The system of claim 19 , wherein the one or more processors are

Assignees

• Netflix Inc

Inventors

• Li Zhi
• Aaron Anne
• Moorthy Anush
• Bampis Christos

Classifications

• H04N19/154 Primary

  Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion (use of rate-distortion criteria H04N19/147) · CPC title

• H04N19/146

  Data rate or code amount at the encoder output · CPC title

• H04N19/593

  involving spatial prediction techniques · CPC title

• H04N21/23418

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• H04N21/23439

  for generating different versions · CPC title