Patents by Inventor David Charles Minnen
David Charles Minnen has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240078712Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.Type: ApplicationFiled: April 25, 2023Publication date: March 7, 2024Inventors: David Charles Minnen, Saurabh Singh, Johannes Balle, Troy Chinen, Sung Jin Hwang, Nicholas Johnston, George Dan Toderici
-
Publication number: 20230419555Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.Type: ApplicationFiled: September 5, 2023Publication date: December 28, 2023Inventors: David Charles Minnen, Saurabh Singh
-
Patent number: 11783511Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.Type: GrantFiled: December 23, 2022Date of Patent: October 10, 2023Assignee: Google LLCInventors: David Charles Minnen, Saurabh Singh
-
Publication number: 20230206512Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.Type: ApplicationFiled: December 23, 2022Publication date: June 29, 2023Inventors: David Charles Minnen, Saurabh Singh
-
Patent number: 11670010Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.Type: GrantFiled: January 19, 2022Date of Patent: June 6, 2023Assignee: Google LLCInventors: David Charles Minnen, Saurabh Singh, Johannes Balle, Troy Chinen, Sung Jin Hwang, Nicholas Johnston, George Dan Toderici
-
Patent number: 11538197Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.Type: GrantFiled: September 15, 2020Date of Patent: December 27, 2022Assignee: Google LLCInventors: David Charles Minnen, Saurabh Singh
-
Patent number: 11354822Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. A request to generate an encoded representation of an input image is received. The encoded representation of the input image is then generated. The encoded representation includes a respective set of binary codes at each iteration. Generating the set of binary codes for the iteration from an initial set of binary includes: for any tiles that have already been masked off during any previous iteration, masking off the tile. For any tiles that have not yet been masked off during any of the previous iterations, a determination is made as to whether a reconstruction error of the tile when reconstructed from binary codes at the previous iterations satisfies an error threshold. When the reconstruction quality satisfies the error threshold, the tile is masked off.Type: GrantFiled: May 16, 2018Date of Patent: June 7, 2022Assignee: Google LLCInventors: Michele Covell, Damien Vincent, David Charles Minnen, Saurabh Singh, Sung Jin Hwang, Nicholas Johnston, Joel Eric Shor, George Dan Toderici
-
Publication number: 20220138991Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.Type: ApplicationFiled: January 19, 2022Publication date: May 5, 2022Inventors: David Charles Minnen, Saurabh Singh, Johannes Balle, Troy Chinen, Sung Jin Hwang, Nicholas Johnston, George Dan Toderici
-
Publication number: 20220084255Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.Type: ApplicationFiled: September 15, 2020Publication date: March 17, 2022Inventors: David Charles Minnen, Saurabh Singh
-
Patent number: 11257254Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.Type: GrantFiled: July 18, 2019Date of Patent: February 22, 2022Assignee: Google LLCInventors: David Charles Minnen, Saurabh Singh, Johannes Balle, Troy Chinen, Sung Jin Hwang, Nicholas Johnston, George Dan Toderici
-
Patent number: 11250595Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. An image encoder system receives a request to generate an encoded representation of an input image that has been partitioned into a plurality of tiles and generates the encoded representation of the input image. To generate the encoded representation, the system processes a context for each tile using a spatial context prediction neural network that has been trained to process context for an input tile and generate an output tile that is a prediction of the input tile. The system determines a residual image between the particular tile and the output tile generated by the spatial context prediction neural network by process the context for the particular tile and generates a set of binary codes for the particular tile by encoding the residual image using an encoder neural network.Type: GrantFiled: May 29, 2018Date of Patent: February 15, 2022Assignee: Google LLCInventors: Michele Covell, Damien Vincent, David Charles Minnen, Saurabh Singh, Sung Jin Hwang, Nicholas Johnston, Joel Eric Shor, George Dan Toderici
-
Patent number: 11177823Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, an encoder neural network processes data to generate an output including a representation of the data as an ordered collection of code symbols. The ordered collection of code symbols is entropy encoded using one or more code symbol probability distributions. A compressed representation of the data is determined based on the entropy encoded representation of the collection of code symbols and data indicating the code symbol probability distributions used to entropy encode the collection of code symbols. In another aspect, a compressed representation of the data is decoded to determine the collection of code symbols representing the data. A reconstruction of the data is determined by processing the collection of code symbols by a decoder neural network.Type: GrantFiled: May 21, 2018Date of Patent: November 16, 2021Assignee: Google LLCInventors: David Charles Minnen, Michele Covell, Saurabh Singh, Sung Jin Hwang, George Dan Toderici
-
Publication number: 20210335017Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. A request to generate an encoded representation of an input image is received. The encoded representation of the input image is then generated. The encoded representation includes a respective set of binary codes at each iteration. Generating the set of binary codes for the iteration from an initial set of binary includes: for any tiles that have already been masked off during any previous iteration, masking off the tile. For any tiles that have not yet been masked off during any of the previous iterations, a determination is made as to whether a reconstruction error of the tile when reconstructed from binary codes at the previous iterations satisfies an error threshold. When the reconstruction quality satisfies the error threshold, the tile is masked off.Type: ApplicationFiled: May 16, 2018Publication date: October 28, 2021Inventors: Michele Covell, Damien Vincent, David Charles Minnen, Saurabh Singh, Sung Jin Hwang, Nicholas Johnston, Joel Eric Shor, George Dan Toderici
-
Patent number: 10713818Abstract: Methods, and systems, including computer programs encoded on computer storage media for compressing data items with variable compression rate. A system includes an encoder sub-network configured to receive a system input image and to generate an encoded representation of the system input image, the encoder sub-network including a first stack of neural network layers including one or more LSTM neural network layers and one or more non-LSTM neural network layers, the first stack configured to, at each of a plurality of time steps, receive an input image for the time step that is derived from the system input image and generate a corresponding first stack output, and a binarizing neural network layer configured to receive a first stack output as input and generate a corresponding binarized output.Type: GrantFiled: January 28, 2019Date of Patent: July 14, 2020Assignee: Google LLCInventors: George Dan Toderici, Sean O'Malley, Rahul Sukthankar, Sung Jin Hwang, Damien Vincent, Nicholas Johnston, David Charles Minnen, Joel Shor, Michele Covell
-
Publication number: 20200111238Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. An image encoder system receives a request to generate an encoded representation of an input image that has been partitioned into a plurality of tiles and generates the encoded representation of the input image. To generate the encoded representation, the system processes a context for each tile using a spatial context prediction neural network that has been trained to process context for an input tile and generate an output tile that is a prediction of the input tile. The system determines a residual image between the particular tile and the output tile generated by the spatial context prediction neural network by process the context for the particular tile and generates a set of binary codes for the particular tile by encoding the residual image using an encoder neural network.Type: ApplicationFiled: May 29, 2018Publication date: April 9, 2020Inventors: Michele Covell, Damien Vincent, David Charles Minnen, Saurabh Singh, Sung Jin Hwang, Nicholas Johnston, Joel Eric Shor, George Dan Toderici
-
Publication number: 20200027247Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.Type: ApplicationFiled: July 18, 2019Publication date: January 23, 2020Inventors: David Charles Minnen, Saurabh Singh, Johannes Balle, Troy Chinen, Sung Jin Hwang, Nicholas Johnston, George Dan Toderici
-
Publication number: 20190356330Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, an encoder neural network processes data to generate an output including a representation of the data as an ordered collection of code symbols. The ordered collection of code symbols is entropy encoded using one or more code symbol probability distributions. A compressed representation of the data is determined based on the entropy encoded representation of the collection of code symbols and data indicating the code symbol probability distributions used to entropy encode the collection of code symbols. In another aspect, a compressed representation of the data is decoded to determine the collection of code symbols representing the data. A reconstruction of the data is determined by processing the collection of code symbols by a decoder neural network.Type: ApplicationFiled: May 21, 2018Publication date: November 21, 2019Inventors: David Charles Minnen, Michele Covell, Saurabh Singh, Sung Jin Hwang, George Dan Toderici
-
Patent number: 10192327Abstract: Methods, and systems, including computer programs encoded on computer storage media for compressing data items with variable compression rate. A system includes an encoder sub-network configured to receive a system input image and to generate an encoded representation of the system input image, the encoder sub-network including a first stack of neural network layers including one or more LSTM neural network layers and one or more non-LSTM neural network layers, the first stack configured to, at each of a plurality of time steps, receive an input image for the time step that is derived from the system input image and generate a corresponding first stack output, and a binarizing neural network layer configured to receive a first stack output as input and generate a corresponding binarized output.Type: GrantFiled: February 3, 2017Date of Patent: January 29, 2019Assignee: Google LLCInventors: George Dan Toderici, Sean O'Malley, Rahul Sukthankar, Sung Jin Hwang, Damien Vincent, Nicholas Johnston, David Charles Minnen, Joel Shor, Michele Covell