-
公开(公告)号：US12010369B2
公开(公告)日：2024-06-11
申请号：US18162698
申请日：2023-01-31
CPC分类号： H04N21/2662 , H04L65/70 , H04L65/75 , H04L65/80
摘要： Embodiments provide for improved stream generation. A first encoded segment is generated by encoding a first segment, of a plurality of segments in a media asset, using a first bitrate of a plurality of bitrates specified in an encoding ladder. A second encoded segment is generated by encoding the first segment using a second bitrate, where the second bitrate is lower than the first bitrate. Upon receiving a request for the first segment at the first bitrate, the second encoded segment is output based at least in part on determining that a first quality of the second encoded segment is within a tolerance of a second quality of the first encoded segment.
-
公开(公告)号：US20230379475A1
公开(公告)日：2023-11-23
申请号：US18230409
申请日：2023-08-04
发明人： Christopher Richard Schroers , Roberto Gerson de Albuquerque Azevedo , Nicholas David Gregory , Yuanyi Xue , Scott Labrozzi , Abdelaziz Djelouah
IPC分类号： H04N19/147 , H04N19/132 , H04N19/184 , G06N3/08 , G06T3/40 , G06T9/00
CPC分类号： H04N19/147 , H04N19/132 , H04N19/184 , G06N3/08 , G06T3/4046 , G06T9/002
摘要： A system includes a machine learning (ML) model-based video downsampler configured to receive an input video sequence having a first display resolution, and to map the input video sequence to a lower resolution video sequence having a second display resolution lower than the first display resolution. The system also includes a neural network-based (NN-based) proxy video codec configured to transform the lower resolution video sequence into a decoded proxy bitstream. In addition, the system includes an upsampler configured to produce an output video sequence using the decoded proxy bitstream.
-
公开(公告)号：US20220329876A1
公开(公告)日：2022-10-13
申请号：US17704692
申请日：2022-03-25
发明人： Abdelaziz Djelouah , Leonhard Markus Helminger , Roberto Gerson de Albuquerque Azevedo , Scott Labrozzi , Christopher Richard Schroers , Yuanyi Xue
摘要： A system processing hard e executes a machine learning (ML) model-based video compression encoder to receive uncompressed video content and corresponding motion compensated video content, compare the uncompressed and motion compensated video content to identify an image space residual, transform the image space residual to a latent space representation of the uncompressed video content, and transform, using a trained image compression ML model, the motion compensated video content to a latent space representation of the motion compensated video content. The ML model-based video compression encoder further encodes the latent space representation of the image space residual to produce an encoded latent residual, encodes, using the trained image compression ML model, the latent space representation of the motion compensated video content to produce an encoded latent video content, and generates, using the encoded latent residual and the encoded latent video content, a compressed video content corresponding to the uncompressed video content.
-
公开(公告)号：US11595716B2
公开(公告)日：2023-02-28
申请号：US17506489
申请日：2021-10-20
摘要： Embodiments provide for improved stream generation. A target average bitrate (TAB) segment is generated by encoding a first segment, of a plurality of segments in a video, using a first maximum average bitrate (MAB) of a plurality of MABs specified in an encoding ladder. An intermediate average bitrate (IAB) segment is generated by encoding the first segment using a first intermediate bitrate, wherein the first intermediate bitrate is lower than the first MAB. Upon receiving a request for the first segment at the first MAB, the IAB segment is output based at least in part on determining that a first quality score of the IAB segment is within a predefined tolerance of a second quality score of the TAB segment.
-
公开(公告)号：US11012718B2
公开(公告)日：2021-05-18
申请号：US16557920
申请日：2019-08-30
发明人： Christopher Schroers , Joaquim Campos , Abdelaziz Djelouah , Yuanyi Xue , Erika Varis Doggett , Jared McPhillen , Scott Labrozzi
IPC分类号： H04N19/91 , G06K9/00 , H04N19/12 , H04N19/124 , G06N3/08
摘要： Systems and methods are disclosed for generating a latent space residual. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining a target frame, obtaining a reconstructed frame, encoding the target frame into a latent space to generate a latent space target frame, encoding the reconstructed frame into the latent space to generate a latent space reconstructed frame, and generating a latent space residual based on the latent space target frame and the latent space reconstructed frame.
-
公开(公告)号：US20210067808A1
公开(公告)日：2021-03-04
申请号：US16557920
申请日：2019-08-30
发明人： Christopher Schroers , Joaquim Campos , Abdelaziz Djelouah , Yuanyi Xue , Erika Varis Doggett , Jared McPhillen , Scott Labrozzi
IPC分类号： H04N19/91 , G06K9/00 , H04N19/124 , G06N3/08 , H04N19/12
摘要： Systems and methods are disclosed for generating a latent space residual. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining a target frame, obtaining a reconstructed frame, encoding the target frame into a latent space to generate a latent space target frame, encoding the reconstructed frame into the latent space to generate a latent space reconstructed frame, and generating a latent space residual based on the latent space target frame and the latent space reconstructed frame.
-
公开(公告)号：US20220337852A1
公开(公告)日：2022-10-20
申请号：US17704722
申请日：2022-03-25
发明人： Abdelaziz Djelouah , Leonhard Markus Helminger , Roberto Gerson de Albuquerque Azevedo , Christopher Richard Schroers , Scott Labrozzi , Yuanyi Xue
IPC分类号： H04N19/42
摘要： A system includes a machine learning (ML) model-based video encoder configured to receive an uncompressed video sequence including multiple video frames, determine, from among the multiple video frames, a first video frame subset and a second video frame subset, encode the first video frame subset to produce a first compressed video frame subset, and identify a first decompression data for the first compressed video frame subset. The ML model-based video encoder is further configured to encode the second video frame subset to produce a second compressed video frame subset, and identify a second decompression data for the second compressed video frame subset. The first decompression data is specific to decoding the first compressed video frame subset but not the second compressed video frame subset, and the second decompression data is specific to decoding the second compressed video frame subset but not the first compressed video frame subset.
-
公开(公告)号：US20210142524A1
公开(公告)日：2021-05-13
申请号：US16811219
申请日：2020-03-06
发明人： Abdelaziz Djelouah , Leonhard Markus Helminger , Scott Labrozzi , Yuanyi Xue , Erika Varis Doggett , Jared McPhillen , Christopher Richard Schroers
IPC分类号： G06T9/00 , H04N19/60 , H04N19/126 , H04N19/91
摘要： According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.
-
公开(公告)号：US12087024B2
公开(公告)日：2024-09-10
申请号：US16811219
申请日：2020-03-06
发明人： Abdelaziz Djelouah , Leonhard Markus Helminger , Scott Labrozzi , Yuanyi Xue , Erika Varis Doggett , Jared McPhillen , Christopher Richard Schroers
IPC分类号： H04N19/60 , G06T9/00 , H04N19/126 , H04N19/91
CPC分类号： G06T9/002 , H04N19/126 , H04N19/60 , H04N19/91
摘要： According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.
-
公开(公告)号：US20240283957A1
公开(公告)日：2024-08-22
申请号：US18653776
申请日：2024-05-02
发明人： Abdelaziz Djelouah , Leonhard Markus Helminger , Roberto Gerson de Albuquerque Azevedo , Christopher Richard Schroers , Scott Labrozzi , Yuanyi Xue
IPC分类号： H04N19/42
CPC分类号： H04N19/42
摘要： A system includes a machine learning (ML) model-based video encoder configured to receive an uncompressed video sequence including multiple video frames, determine, from among the multiple video frames, a first video frame subset and a second video frame subset, encode the first video frame subset to produce a first compressed video frame subset, and identify a first decompression data for the first compressed video frame subset. The ML model-based video encoder is further configured to encode the second video frame subset to produce a second compressed video frame subset, and identify a second decompression data for the second compressed video frame subset. The first decompression data is specific to decoding the first compressed video frame subset but not the second compressed video frame subset, and the second decompression data is specific to decoding the second compressed video frame subset but not the first compressed video frame subset.
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.016 秒)
