公开(公告)号：US11563986B1

公开(公告)日：2023-01-24

申请号：US17551086

申请日：2021-12-14

Applicant: NETFLIX, INC.

Inventor： Christos G. Bampis ,  Li-Heng Chen ,  Aditya Mavlankar ,  Anush Moorthy

IPC: H04N19/86 ,  H04N19/186 ,  H04N19/30 ,  H04N19/132 ,  G06N3/04 ,  H04N19/89

Abstract: In various embodiments, a training application trains a machine learning model to preprocess images. In operation, the training application computes a chroma sampling factor based on a downscaling factor and a chroma subsampling ratio. The training application executes a machine learning model that is associated with the chroma sampling factor on data that corresponds to both an image and a first chroma component to generate preprocessed data corresponding to the first chroma component. Based on the preprocessed data, the training application updates at least one parameter of the machine learning model to generate a trained machine learning model that is associated with the first chroma component.

公开(公告)号：US11532077B2

公开(公告)日：2022-12-20

申请号：US16995680

申请日：2020-08-17

Applicant: NETFLIX, INC.

Inventor： Li-Heng Chen ,  Christos G. Bampis ,  Zhi Li

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/90 ,  H04N21/234

Abstract: In various embodiments, a quality inference application estimates the perceived quality of reconstructed videos. The quality inference application computes a first feature value for a first feature included in a feature vector based on a color component associated with a reconstructed video. The quality inference application also computes a second feature value for a second feature included in the feature vector based on a brightness component associated with the reconstructed video. Subsequently, the quality inference application computes a perceptual quality score based on the first feature value and the second feature value. The perceptual quality score indicates a level of visual quality associated with at least one frame included in the reconstructed video.

公开(公告)号：US11948271B2

公开(公告)日：2024-04-02

申请号：US17133206

申请日：2020-12-23

Applicant: NETFLIX, INC.

Inventor： Li-Heng Chen ,  Christos G. Bampis ,  Zhi Li

IPC: G06T3/40 ,  G06N3/084 ,  G06T3/4046 ,  G06T9/00

CPC classification number: G06T3/4046 ,  G06N3/084 ,  G06T9/002

Abstract: In various embodiments, a training application trains a convolutional neural network to downsample images in a video encoding pipeline. The convolution neural network includes at least two residual blocks and is associated with a downsampling factor. The training application executes the convolutional neural network on a source image to generate a downsampled image. The training application then executes an upsampling algorithm on the downsampled image to generate a reconstructed image having the same resolution as the source image. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates at least one parameter of the convolutional neural network based on the reconstruction error to generate a trained convolutional neural network. Advantageously, the trained convolution neural network can be implemented in a video encoding pipeline to mitigate visual quality reductions typically experienced with conventional video encoding pipelines that implement conventional downsampling techniques.

公开(公告)号：US11557025B2

公开(公告)日：2023-01-17

申请号：US16995677

申请日：2020-08-17

Applicant: NETFLIX, INC.

Inventor： Li-Heng Chen ,  Christos G. Bampis ,  Zhi Li

IPC: G06T7/00 ,  G06T7/90

Abstract: In various embodiments, a training application generates a perceptual video model. The training application computes a first feature value for a first feature included in a feature vector based on a first color component associated with a first reconstructed training video. The training application also computes a second feature value for a second feature included in the feature vector based on a first brightness component associated with the first reconstructed training video. Subsequently, the training application performs one or more machine learning operations based on the first feature value, the second feature value, and a first subjective quality score for the first reconstructed training video to generate a trained perceptual quality model. The trained perceptual quality model maps a feature value vector for the feature vector to a perceptual quality score.