Device-consistent techniques for predicting absolute perceptual video quality

Patent metadata

Field	Value
Publication number	US-10834406-B2
Application number	US-201715782590-A
Country	US
Kind code	B2
Filing date	Oct 12, 2017
Priority date	Dec 12, 2016
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

In various embodiments, a perceptual quality application determines an absolute quality score for encoded video content viewed on a target viewing device. In operation, the perceptual quality application determines a baseline absolute quality score for the encoded video content viewed on a baseline viewing device. Subsequently, the perceptual quality application determines that a target value for a type of the target viewing device does not match a base value for the type of the baseline viewing device. The perceptual quality application computes an absolute quality score for the encoded video content viewed on the target viewing device based on the baseline absolute quality score and the target value. Because the absolute quality score is independent of the viewing device, the absolute quality score accurately reflects the perceived quality of a wide range of encoded video content when decoded and viewed on a viewing device.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
determining a first absolute quality score indicating a predicted quality of first encoded video content viewed on a baseline viewing device;
determining that a first value of a first type for a first viewing device is not equal to a base value of the first type for the baseline viewing device;
computing a second absolute quality score indicating a predicted quality of the first encoded video content viewed on the first viewing device based on the first absolute quality score and the first value; and
comparing the first encoded video content to another encoded video content based on the second absolute quality score or transmitting at least a portion of the first encoded video content based on the second absolute quality score.

2. The computer-implemented method of claim 1 , wherein the first type comprises a device type, and the first value indicates a mobile device, a laptop device, or a television device.

3. The computer-implemented method of claim 1 , wherein computing the second absolute quality score comprises:
selecting a first device relationship based on the first value, wherein the first device relationship associates a base absolute quality score indicating a predicted quality of encoded video content viewed on the baseline device and an absolute quality score indicating a predicted quality of the encoded video content viewed on a third viewing device; and
mapping the first absolute quality score to the second absolute quality score based on the first device relationship.

4. The computer-implemented method of claim 3 , wherein the first device relationship comprises a polynomial relating to the first value for the first type.

5. The computer-implemented method of claim 3 , further comprising generating the first device relationship based on a first set of mean opinion scores associated with the baseline viewing device and a second set of mean opinion scores associated with the third viewing device.

6. The computer-implemented method of claim 5 , further comprising computing a first mean opinion score included in the first set of mean opinion scores based on a first plurality of human-observed quality scores assigned while viewing re-constructed training video content derived from encoded training video content on the baseline viewing device.

7. The computer-implemented method of claim 1 , wherein determining the first absolute quality score comprises:
computing a first set of objective values for a set of quality metrics based on the first encoded video content; and
computing the first absolute quality score based on the first set of objective values and a first model.

8. The computer-implemented method of claim 7 , wherein the first model is included in a plurality of models, and further comprising selecting the first model based on a first spatial resolution of first video content from which the first encoded video content is derived.

9. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to perform the steps of:
determining a first absolute quality score indicating a predicted quality of first encoded video content viewed on a baseline viewing device;
selecting a first device relationship based on a first value of a first type for a first viewing device;
computing a second absolute quality score indicating a predicted quality of the first encoded video content viewed on the first viewing device based on the first absolute quality score and the first device relationship; and
comparing the first encoded video content to another encoded video content based on the second absolute quality score or transmitting at least a portion of the first encoded video content based on the second absolute quality score.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the first type comprises a spatial resolution, and the first value indicates 480p, 720p, 1080p, or 4K.

11. The non-transitory computer-readable storage medium of claim 9 , wherein the first type comprises a device type, and the first value indicates a mobile device, a laptop device, or a television device.

12. The non-transitory computer-readable storage medium of claim 9 , wherein the first device relationship associates a base absolute quality score indicating a predicted quality of encoded video content viewed on the baseline device and an absolute quality score indicating a predicted quality of the encoded video content viewed on a third viewing device, and computing the second absolute quality score comprises mapping the first absolute quality score to the second absolute quality score based on the first device relationship.

13. The non-transitory computer-readable storage medium of claim 12 , the steps further comprising generating the first device relationship based on a first set of mean opinion scores associated with the baseline viewing device and a second set of mean opinion scores associated with the third viewing device.

14. The non-transitory computer-readable storage medium of claim 13 , the steps further comprising performing one or more curve fitting operations on a plot to generate a second-order polynomial that comprises the first device relationship, wherein the plot includes the first set of mean opinion scores associated with the baseline viewing device and the second set of mean opinion scores associated with the third viewing device.

15. The non-transitory computer-readable storage medium of claim 9 , wherein determining the first absolute quality score comprises:
computing a first set of objective values for a set of quality metrics based on the first encoded video content; and
computing the first absolute quality score based on the first set of objective values and a first model.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the first model is included in a plurality of models, and the steps further comprise selecting the first model based on a first spatial resolution of first video content from which the first encoded video content is derived.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the first model associates a set of objective values for the set of objective quality metrics with an absolute quality score.

18. A system comprising:
a memory storing a perceptual quality application; and
a processor coupled to the memory, wherein when executed by the processor, the perceptual quality application causes the processor to:
compute a first absolute quality score indicating a predicted quality of first encoded video content viewed on a baseline viewing device,
determine that a first device relationship is applicable to a first viewing device based on a first value of a first type for the first viewing device,
compute a second absolute quality score indicating a predicted quality of the first encoded video content viewed on the first viewing device based on the first device relationship and the first absolute quality score, and
compare the first encoded video content to another encoded video content based on the second absolute quality score or transmit at least a portion of the first encoded video content based on the second absolute quality score.

19. The system of claim 18 , wherein the first type comprises a device type, and the first value indicates a mobile device, a laptop device, or a television device.

20. The system of claim 18 , wherein the first device relationship comprise

Assignees

• Netflix Inc

Inventors

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

Classifications

• H04N19/146

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

• 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

• H04N17/004

  for digital television systems · CPC title

• H04N19/593

  involving spatial prediction techniques · CPC title

• H04N21/23439

  for generating different versions · CPC title