-
公开(公告)号：US20230299788A1
公开(公告)日：2023-09-21
申请号：US18008045
申请日：2021-06-03
申请人： Google LLC
IPC分类号： H03M7/30 , G06N3/0455 , G06N3/084
CPC分类号： H03M7/3059 , G06N3/0455 , G06N3/084
摘要： A computer-implemented method for compressing computer-readable data having improved efficiency can include obtaining, by a computing system including one or more computing devices, input data associated with the computing system; and encoding, by the computing system, the input data and added noise from a noisy channel to produce encoded data based at least in part on an encoder model, wherein encoding the input data and added noise includes additively combining the added noise and the input data to obtain noisy input data and rounding the noisy input data by a soft rounding function, the soft rounding function having a sharpness, to produce the encoded data, wherein the machine-learned encoder model is trained on training data, wherein the training data is encoded with the added noise from the noisy channel.
-
公开(公告)号：US20230099526A1
公开(公告)日：2023-03-30
申请号：US17486359
申请日：2021-09-27
申请人： Google LLC
摘要： Example aspects of the present disclosure are directed to a computer-implemented method for determining a perceptual quality of a subject video content item. The method can include inputting a subject frame set from the subject video content item into a first machine-learned model. The method can also include generating, using the first machine-learned model, a feature based at least in part on the subject frame set. The method can also include outputting, using a second machine-learned model, a score indicating the perceptual quality of the subject video content item based at least in part on the feature.
-
公开(公告)号：US20240223817A1
公开(公告)日：2024-07-04
申请号：US18563734
申请日：2022-07-05
申请人： Google LLC
发明人： George Dan Toderici , Eirikur Thor Agustsson , Fabian Julius Mentzer , David Charles Minnen , Johannes Balle , Nicholas Johnston
IPC分类号： H04N19/91 , G06T3/18 , G06T5/70 , H04N19/124 , H04N19/137
CPC分类号： H04N19/91 , G06T3/18 , G06T5/70 , H04N19/124 , H04N19/137 , G06T2207/20084
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing video data. In one aspect, a method comprises: receiving a video sequence of frames; generating, using a flow prediction network, an optical flow between two sequential frames, wherein the two sequential frames comprise a first frame and a second frame that is subsequent the first frame; generating from the optical flow, using a first autoencoder neural network: a predicted optical flow between the first frame and the second frame; and warping a reconstruction of the first frame according to the predicted optical flow and subsequently applying a blurring operation to obtain an initial predicted reconstruction of the second frame.
-
公开(公告)号：US20240107079A1
公开(公告)日：2024-03-28
申请号：US18238068
申请日：2023-08-25
申请人： Google LLC
发明人： George Dan Toderici , Fabian Julius Mentzer , Eirikur Thor Agustsson , Michael Tobias Tschannen
IPC分类号： H04N19/91 , G06N3/045 , G06N3/088 , H04N19/124 , H04N19/154
CPC分类号： H04N19/91 , G06N3/045 , G06N3/088 , H04N19/124 , H04N19/154
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.
-
公开(公告)号：US11750848B2
公开(公告)日：2023-09-05
申请号：US17107684
申请日：2020-11-30
申请人： Google LLC
发明人： George Dan Toderici , Fabian Julius Mentzer , Eirikur Thor Agustsson , Michael Tobias Tschannen
IPC分类号： G06V10/00 , H04N19/91 , H04N19/124 , G06N3/088 , H04N19/154 , G06N3/045
CPC分类号： H04N19/91 , G06N3/045 , G06N3/088 , H04N19/124 , H04N19/154
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.
-
公开(公告)号：US20220174328A1
公开(公告)日：2022-06-02
申请号：US17107684
申请日：2020-11-30
申请人： Google LLC
发明人： George Dan Toderici , Fabian Julius Mentzer , Eirikur Thor Agustsson , Michael Tobias Tschannen
IPC分类号： H04N19/91 , H04N19/124 , H04N19/154 , G06N3/08 , G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. In one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.012 秒)
