Techniques for efficiently performing subsequence-based encoding for a media title

Patent metadata

Field	Value
Publication number	US-11019374-B2
Application number	US-202016780752-A
Country	US
Kind code	B2
Filing date	Feb 3, 2020
Priority date	Feb 4, 2019
Publication date	May 25, 2021
Grant date	May 25, 2021

Abstract

In various embodiments, an interpolation-based encoding application encodes a first subsequence included in a media title at each encoding point included in a first set of encoding points to generate encoded subsequences. Subsequently, the interpolation-based encoding application performs interpolation operation(s) based on the encoded subsequences to estimate a first media metric value associated with a first encoding point that is not included in the first set of encoding points. The interpolation-based encoding application then generates an encoding recipe based on the encoded subsequences and the first media metric value. The encoding recipe specifies a different encoding point for each subsequence included in the media title. After determining that the encoding recipe specifies the first encoding point for the first subsequence, the interpolation-based encoding application encodes the first subsequence at the first encoding point to generate at least a portion of an encoded version of the media title.

First claim

What is claimed is:

1. A computer-implemented method for encoding a media title, the method comprising:
encoding a first subsequence included in the media title across a first plurality of encoding points to generate a first plurality of encoded subsequences;
performing one or more interpolation operations based on the first plurality of encoded subsequences to estimate a first media metric value associated with a first encoding point that is not included in the first plurality of encoding points;
generating a first encoding recipe that specifies a different encoding point for each subsequence included in the media title based on the first plurality of encoded subsequences and the first media metric value;
determining that the first encoding recipe specifies the first encoding point for the first subsequence; and
encoding the first subsequence at the first encoding point to generate at least a portion of a first encoded version of the media title.

2. The method of claim 1 wherein the first media metric value comprises a value for a bitrate, a size, a peak signal-to-noise-ratio, a linear video multimethod assessment fusion metric, or a harmonic video multimethod assessment fusion.

3. The method of claim 1 , wherein each encoding point included in the first plurality of encoding points is associated with a different value of an encoding parameter.

4. The method of claim 1 , wherein the first media metric value comprises a first value of a visual quality metric, and performing the one or more interpolation operations comprises:
decoding the first plurality of encoded subsequences to generate a plurality of reconstructed subsequences;
computing a plurality of values for the visual quality metric based on the plurality of reconstructed subsequences; and
interpolating between two values included in the plurality of values for the visual quality metric to estimate the first value of the visual quality metric.

5. The method of claim 1 , wherein the first media metric value comprises a first bitrate, and performing the one or more interpolation operations comprises:
determining a plurality of bitrates based of the first plurality of encoded subseqeuences; and
interpolating between two bitrates included in the plurality of bitrates to estimate the first bitrate.

6. The method of claim 1 , wherein generating the first encoding recipe comprises:
performing one or more interpolation operations based on the first plurality of encoded subsequences to estimate a first bitrate associated with the first encoding point;
performing one or more optimization operations based on the first plurality of encoded subsequences, the first media metric value, and the first bitrate to generate a plurality of encoding recipes; and
determining the first encoding recipe from the plurality of encoding recipes based on a first target bitrate or a first target value for the visual quality metric.

7. The method of claim 6 , further comprising:
determining a second encoding recipe from the plurality of encoding recipes based on a second target bitrate or a second target value for the visual quality metric; and
generating a second encoded version of the media title based on the second encoding recipe.

8. The method of claim 1 , wherein generating the first encoding recipe comprises:
generating a first convex hull of rate-quality points based on the first plurality of encoded subsequences and the first media metric value;
generating a global convex hull of encoding recipes based on the first convex hull and a second convex hull that is associated with a second subsequence included in the media title; and
determining the first encoding recipe from the global convex hull based on a target bitrate or a target level of visual quality.

9. The method of claim 1 , wherein the at least a portion of the first encoded version of the media title comprises a first encoded subsequence, and the first encoded version of the media title is further generated by:
determining that the first encoding recipe specifies a second encoding point for a second subsequence included in the media title;
determining that a second encoded subsequence is associated with both the second encoding point and the second subsequence; and
aggregating the first encoded subsequence and the second encoded subsequence to generate at least an additional portion of the first encoded version of the media title.

10. The method of claim 1 , wherein the one or more interpolation operations comprise at least one Piecewise Cubic Hermite Interpolating operation, Polynomial interpolation operation, linear interpolation operation, quadratic interpolation operation, cubic interpolation operation, Akima spline operation, or cubic spline operation.

11. 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 encode a media title by performing the steps of:
encoding a first subsequence included in the media title across a first plurality of encoding points to generate a first plurality of encoded subsequences;
performing one or more interpolation operations based on the first plurality of encoded subsequences to compute a plurality of estimated media metric values associated with a second plurality of encoding points;
generating a first encoding recipe that specifies a different encoding point for each subsequence included in the media title based on the first plurality of encoded subsequences and the plurality of estimated media metric values;
determining that the first encoding recipe specifies a first encoding point for the first subsequence, wherein the first encoding point is not included in the first plurality of encoding points; and
encoding the first subsequence at the first encoding point to generate at least a portion of a first encoded version of the media title.

12. The one or more non-transitory computer readable media of claim 11 , wherein each estimated media metric value included in the plurality of estimated media metric values comprises a different value for a bitrate, a size, a peak signal-to-noise-ratio, a linear video multimethod assessment fusion metric, or a harmonic video multimethod assessment fusion.

13. The one or more non-transitory computer readable media of claim 11 , wherein each encoding point included in the first plurality of encoding points is associated with a different value of an encoding parameter.

14. The one or more non-transitory computer readable media of claim 11 , wherein the plurality of estimated media metric values comprises a plurality of estimated values for a visual quality metric, and performing the one or more interpolation operations comprises:
decoding the first plurality of encoded subsequences to generate a plurality of reconstructed subsequences;
computing a plurality of values for the visual quality metric based on the plurality of reconstructed subsequences; and
interpolating between at least two values included in the plurality of values for the visual quality metric to compute the plurality of estimated values for the visual quality metric.

15. The one or more non-transitory computer readable media of claim 11 , wherein the plurality of estimated media metric values comprises a plurality of estimated bitrates, and performing the one or more interpolation operations comprises:
determining a plurality of bitrates based of the first plurality of encoded subseqeuences; and
interpolating between at least two bitrates included in the plurality of bitrates to compute the plurality of estimated bitrates.

Assignees

• Netflix Inc

Inventors

• Wallendael Glenn Van
• Aaron Anne
• Swanson Kyle
• De Cock Jan
• Guo Liwei
• Bhaskar Sonia

Classifications

• H04L65/765

  intermediate · CPC title

• H04L65/762

  at the source  (reformatting of additional data in video distribution servers H04N21/2355) · CPC title

• H04L65/70

  Media network packetisation · CPC title

• H04L65/612

  for unicast · CPC title

• H04N21/234354

  by altering signal-to-noise ratio parameters, e.g. requantization · CPC title