公开(公告)号：US11361416B2

公开(公告)日：2022-06-14

申请号：US16352757

申请日：2019-03-13

Applicant: NETFLIX, INC.

Inventor： Christos Bampis ,  Zhi Li ,  Lavanya Sharan ,  Julie Novak ,  Martin Tingley

IPC: H04N19/154 ,  G06T7/00 ,  G06K9/62 ,  G06N20/20 ,  H04N21/25 ,  H04N19/147 ,  H04N17/00

Abstract: In various embodiments, an encoding metric comparison application computes a first set of quality scores associated with a test encoding configuration based on a set of bootstrap quality models. Each bootstrap quality model is trained based on a different subset of a training database. The encoding metric comparison application computes a second set of quality scores associated with a reference encoding configuration based on the set of bootstrap quality models. Subsequently, the encoding metric comparison application generates a distribution of bootstrap values for an encoding comparison metric based on the first set of quality scores and the second set of quality scores. The distribution quantifies an accuracy of a baseline value for the encoding comparison metric generated by a baseline quality model.

公开(公告)号：US10887602B2

公开(公告)日：2021-01-05

申请号：US15890709

申请日：2018-02-07

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/91 ,  H04N21/235 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N20/20 ,  G06N20/10 ,  G06N5/00 ,  H04N17/00

Abstract: In various embodiments, a prediction application computes a quality score for re-constructed visual content that is derived from visual content. The prediction application generates a frame difference matrix based on two frames included in the re-constructed video content. The prediction application then generates a first entropy matrix based on the frame difference matrix and a first scale. Subsequently, the prediction application computes a first value for a first temporal feature based on the first entropy matrix and a second entropy matrix associated with both the visual content and the first scale. The prediction application computes a quality score for the re-constructed video content based on the first value, a second value for a second temporal feature associated with a second scale, and a machine learning model that is trained using subjective quality scores. The quality score indicates a level of visual quality associated with streamed video content.

公开(公告)号：US11758148B2

公开(公告)日：2023-09-12

申请号：US17093449

申请日：2020-11-09

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Anne Aaron ,  Anush Moorthy ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/59 ,  H04N21/647 ,  H04N19/146 ,  H04N21/234 ,  H04N21/2343 ,  H04N17/00 ,  H04N19/00 ,  H04N19/593

CPC classification number: H04N19/154 ,  H04N17/004 ,  H04N19/00 ,  H04N19/146 ,  H04N19/59 ,  H04N19/593 ,  H04N21/23418 ,  H04N21/23439 ,  H04N21/647

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.

公开(公告)号：US10721477B2

公开(公告)日：2020-07-21

申请号：US15890710

申请日：2018-02-07

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Christos Bampis

IPC: H04N19/154 ,  H04N21/235 ,  G06N20/20 ,  G06K9/00 ,  G06K9/03 ,  H04N19/136 ,  G06T7/00 ,  G06N3/08 ,  G06K9/62 ,  H04N19/91

Abstract: In various embodiments, an ensemble prediction application computes a quality score for re-constructed visual content that is derived from visual content. The ensemble prediction application computes a first quality score for the re-constructed video content based on a first set of values for a first set of features and a first model that associates the first set of values with the first quality score. The ensemble prediction application computes a second quality score for the re-constructed video content based on a second set of values for a second set of features and a second model that associates the second set of values with the second quality score. Subsequently, the ensemble prediction application determines an overall quality score for the re-constructed video content based on the first quality score and the second quality score. The overall quality score indicates a level of visual quality associated with streamed video content.

公开(公告)号：US12075104B2

公开(公告)日：2024-08-27

申请号：US16352755

申请日：2019-03-13

Applicant: NETFLIX, INC.

Inventor： Christos Bampis ,  Zhi Li ,  Lavanya Sharan ,  Julie Novak ,  Martin Tingley

IPC: G06T7/00 ,  G06F18/214 ,  G06N20/20 ,  G06V10/774 ,  H04N19/154 ,  H04N21/25 ,  H04N17/00 ,  H04N19/147

CPC classification number: H04N21/252 ,  G06F18/214 ,  G06N20/20 ,  G06T7/0002 ,  G06V10/774 ,  H04N19/154 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30168 ,  H04N17/004 ,  H04N19/147

Abstract: In various embodiments, a bootstrapping training subsystem performs sampling operation(s) on a training database that includes subjective scores to generate resampled dataset. For each resampled dataset, the bootstrapping training subsystem performs machine learning operation(s) to generate a different bootstrap perceptual quality model. The bootstrapping training subsystem then uses the bootstrap perceptual quality models to quantify the accuracy of a perceptual quality score generated by a baseline perceptual quality model for a portion of encoded video content. Advantageously, relative to prior art solutions in which the accuracy of a perceptual quality score is unknown, the bootstrap perceptual quality models enable developers and software applications to draw more valid conclusions and/or more reliably optimize encoding operations based on the perceptual quality score.

公开(公告)号：US10834406B2

公开(公告)日：2020-11-10

申请号：US15782590

申请日：2017-10-12

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Anne Aaron ,  Anush Moorthy ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/59 ,  H04N21/647 ,  H04N19/146 ,  H04N21/234 ,  H04N21/2343 ,  H04N17/00 ,  H04N19/00 ,  H04N19/593

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.

公开(公告)号：US11683545B2

公开(公告)日：2023-06-20

申请号：US17700231

申请日：2022-03-21

Applicant: NETFLIX, INC.

Inventor： Christos Bampis ,  Zhi Li

IPC: H04N21/24 ,  H04N21/25 ,  H04N21/658 ,  H04N21/4425 ,  H04N21/6547 ,  H04N21/475

CPC classification number: H04N21/2407 ,  H04N21/251 ,  H04N21/4425 ,  H04N21/4756 ,  H04N21/6547 ,  H04N21/6582

Abstract: In various embodiments, a quality of experience (QoE) prediction application computes a visual quality score associated with a stream of encoded video content. The QoE prediction application also determines a rebuffering duration associated with the stream of encoded video content. Subsequently, the QoE prediction application computes an overall QoE score associated with the stream of encoded video content based on the visual quality score, the rebuffering duration, and an exponential QoE model. The exponential QoE model is generated using a plurality of subjective QoE scores and a linear regression model. The overall QoE score indicates a quality level of a user experience when viewing reconstructed video content derived from the stream of encoded video content.

公开(公告)号：US10798387B2

公开(公告)日：2020-10-06

申请号：US15782586

申请日：2017-10-12

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Anne Aaron ,  Anush Moorthy ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/59 ,  H04N21/647 ,  H04N19/146 ,  H04N21/234 ,  H04N21/2343 ,  H04N17/00 ,  H04N19/00 ,  H04N19/593

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.

公开(公告)号：US11729396B2

公开(公告)日：2023-08-15

申请号：US17141075

申请日：2021-01-04

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/91 ,  H04N21/235 ,  G06N3/08 ,  G06N20/20 ,  G06N20/10 ,  H04N17/00 ,  G06F18/2411 ,  G06N3/045 ,  G06N5/01

CPC classification number: H04N19/154 ,  G06F18/2411 ,  G06N3/045 ,  G06N3/08 ,  G06N5/01 ,  G06N20/10 ,  G06N20/20 ,  H04N17/004 ,  H04N19/91 ,  H04N21/235

Abstract: In various embodiments, a prediction application computes a quality score for re-constructed visual content that is derived from visual content. The prediction application generates a frame difference matrix based on two frames included in the re-constructed video content. The prediction application then generates a first entropy matrix based on the frame difference matrix and a first scale. Subsequently, the prediction application computes a first value for a first temporal feature based on the first entropy matrix and a second entropy matrix associated with both the visual content and the first scale. The prediction application computes a quality score for the re-constructed video content based on the first value, a second value for a second temporal feature associated with a second scale, and a machine learning model that is trained using subjective quality scores. The quality score indicates a level of visual quality associated with streamed video content.

公开(公告)号：US11700383B2

公开(公告)日：2023-07-11

申请号：US17141081

申请日：2021-01-04

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Christos Bampis

IPC: H04N19/154 ,  H04N19/91 ,  H04N21/235 ,  G06N3/08 ,  G06N20/20 ,  G06N20/10 ,  H04N17/00 ,  G06F18/2411 ,  G06N3/045 ,  G06N5/01

CPC classification number: H04N19/154 ,  G06F18/2411 ,  G06N3/045 ,  G06N3/08 ,  G06N5/01 ,  G06N20/10 ,  G06N20/20 ,  H04N17/004 ,  H04N19/91 ,  H04N21/235

Abstract: In various embodiments, a prediction application computes a quality score for re-constructed visual content that is derived from visual content. The prediction application generates a frame difference matrix based on two frames included in the re-constructed video content. The prediction application then generates a first entropy matrix based on the frame difference matrix and a first scale. Subsequently, the prediction application computes a first value for a first temporal feature based on the first entropy matrix and a second entropy matrix associated with both the visual content and the first scale. The prediction application computes a quality score for the re-constructed video content based on the first value, a second value for a second temporal feature associated with a second scale, and a machine learning model that is trained using subjective quality scores. The quality score indicates a level of visual quality associated with streamed video content.