公开(公告)号：US20240171737A1

公开(公告)日：2024-05-23

申请号：US18425405

申请日：2024-01-29

申请人： WaveOne Inc.

发明人： Lubomir Bourdev ,  Alexander G. Anderson ,  Kedar Tatwawadi ,  Sanjay Nair ,  Craig Lytle ,  Hervé Guihot ,  Brandon Sprague ,  Oren Rippel

IPC分类号： H04N19/117 ,  G06N3/04 ,  G06N20/00 ,  H04N19/42

CPC分类号： H04N19/117 ,  G06N3/04 ,  G06N20/00 ,  H04N19/42

摘要： A cloud service system manages a filter repository including filters for encoding and decoding media content (e.g. text, image, audio, video, etc.). The cloud service system may receive a request from a client device to provide a filter for installation on a node such as an endpoint device (e.g. pipeline node). The request includes information such as a type of bitstream to be processed by the requested filter. The request may further include other information such as hardware configuration and functionality attribute. The cloud service system may access the filter repository that stores the plurality of filters including encoder filters and decoder filters and may select a filter that is configured to process the type of bitstream identified in the request and provide the selected filter to the client device.

公开(公告)号：US11100394B2

公开(公告)日：2021-08-24

申请号：US16918436

申请日：2020-07-01

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06K9/66 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system applies trained models to compress binary code of an input image to a target codelength. For a set of binary codes representing the quantized coefficents of an input image, the DLBC system applies a first model that is trained to predict feature probabilities based on the context of each bit of the binary codes. The DLBC system compresses the binary code via adaptive arithmetic coding based on the determined probability of each bit. The compressed binary code represents a balance between a reconstruction quality of a reconstruction of the input image and a target compression ratio of the compressed binary code.

公开(公告)号：US10977553B2

公开(公告)日：2021-04-13

申请号：US16406323

申请日：2019-05-08

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06K9/66 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system generates a progressive representation of the encoded input image such that a client device that requires the encoded input image at a particular target bitrate can readily be transmitted the appropriately encoded data. More specifically, the DLBC system computes a representation that includes channels and bitplanes that are ordered based on importance. For a given target rate, the DLBC system truncates the representation according to a trained zero mask to generate the progressive representation. Transmitting a first portion of the progressive representation enables a client device with the lowest target bitrate to appropriately playback the content. Each subsequent portion of the progressive representation allows the client device to playback the content with improved quality.

公开(公告)号：US10748062B2

公开(公告)日：2020-08-18

申请号：US15439895

申请日：2017-02-22

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  H04N19/91 ,  H04N19/149 ,  H04N19/48 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/44 ,  G06K9/66 ,  G06T5/00 ,  H04N19/13 ,  H04N19/18 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system applies trained models to compress binary code of an input image to a target codelength. For a set of binary codes representing the quantized coefficents of an input image, the DLBC system applies a first model that is trained to predict feature probabilities based on the context of each bit of the binary codes. The DLBC system compresses the binary code via adaptive arithmetic coding based on the determined probability of each bit. The compressed binary code represents a balance between a reconstruction quality of a reconstruction of the input image and a target compression ratio of the compressed binary code.

公开(公告)号：US20240073435A1

公开(公告)日：2024-02-29

申请号：US18505470

申请日：2023-11-09

申请人： WaveOne Inc.

发明人： Oren RIPPEL ,  Lubomir BOURDEV

IPC分类号： H04N19/42 ,  G06F18/214 ,  G06N3/08 ,  G06V10/774 ,  G06V10/82 ,  G06V20/40 ,  H04N19/182 ,  H04N19/517

CPC分类号： H04N19/42 ,  G06F18/214 ,  G06N3/08 ,  G06V10/774 ,  G06V10/82 ,  G06V20/46 ,  H04N19/182 ,  H04N19/517 ,  G06N3/084

摘要： An autoencoder is configured to encode content at different quality levels. The autoencoder includes an encoding system and a decoding system with neural network layers forming an encoder network and a decoder network. The encoder network and decoder network are configured to include branching paths through the networks that include different subnetworks. During deployment, content is provided to the encoding system with a quality signal indicating a quality at which the content can be reconstructed. The quality signal determines which of the paths through the encoder network are activated for encoding the content into one or more tensors, which are compressed into a bitstream and later used by the decoding system to reconstruct the content. The autoencoder is trained by randomly or systematically selecting different combinations of tensors to use to encode content and backpropagating error values from loss functions through the network paths associated with the selected tensors.

公开(公告)号：US11917142B2

公开(公告)日：2024-02-27

申请号：US17374826

申请日：2021-07-13

申请人： WaveOne Inc.

发明人： Lubomir Bourdev ,  Alexander G. Anderson ,  Kedar Tatwawadi ,  Sanjay Nair ,  Craig Lytle ,  Hervé Guihot ,  Brandon Sprague ,  Oren Rippel

IPC分类号： H04N19/42 ,  H04N19/117 ,  G06N20/00 ,  G06N3/04

CPC分类号： H04N19/117 ,  G06N3/04 ,  G06N20/00 ,  H04N19/42

摘要： A cloud service system manages a filter repository including filters for encoding and decoding media content (e.g. text, image, audio, video, etc.). The cloud service system may receive a request from a client device to provide a filter for installation on a node such as an endpoint device (e.g. pipeline node). The request includes information such as a type of bitstream to be processed by the requested filter. The request may further include other information such as hardware configuration and functionality attribute. The cloud service system may access the filter repository that stores the plurality of filters including encoder filters and decoder filters and may select a filter that is configured to process the type of bitstream identified in the request and provide the selected filter to the client device.

公开(公告)号：US20220224914A1

公开(公告)日：2022-07-14

申请号：US17466797

申请日：2021-09-03

申请人： WaveOne Inc.

发明人： Alexander G. Anderson ,  Oren Rippel ,  Kedar Tatwawadi ,  Sanjay Nair ,  Craig Lytle ,  Hervé Guihot ,  Brandon Sprague ,  Lubomir Bourdev

IPC分类号： H04N19/149 ,  H04N19/65 ,  H04N19/172 ,  H04N19/166 ,  H04N19/114 ,  G06N3/04

摘要： A compression system trains a machine-learned compression model that includes components for an encoder and decoder. In one embodiment, the compression model is trained to receive parameter information on how a target frame should be encoded with respect to one or more encoding parameters, and encodes the target frame according to the respective values of the encoding parameters for the target frame. In particular, the encoder of the compression model includes at least an encoding system configured to encode a target frame and generate compressed code that can be transmitted by, for example, a sender system to a receiver system. The decoder of the compression model includes a decoding system trained in conjunction with the encoding system. The decoding system is configured to receive the compressed code for the target frame and reconstruct the target frame for the receiver system.

公开(公告)号：US10565499B2

公开(公告)日：2020-02-18

申请号：US15844452

申请日：2017-12-15

申请人： WaveOne Inc.

发明人： Lubomir Bourdev ,  Carissa Lew ,  Sanjay Nair ,  Oren Rippel

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06K9/66 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： An enhanced encoder system generates residual bitstreams representing additional image information that can be used by an image enhancement system to improve a low quality image. The enhanced encoder system upsamples a low quality image and compares the upsampled image to a true high quality image to determine image inaccuracies that arise due to the upsampling process. The enhanced encoder system encodes the information describing the image inaccuracies using a trained encoder model as the residual bitstream. The image enhancement system upsamples the same low quality image to obtain a prediction of a high quality image that can include image inaccuracies. Given the residual bitstream, the image enhancement system decodes the residual bitstream using a trained decoder model and uses the additional image information to improve the predicted high quality image. The image enhancement system can provide an improved, high quality image for display.

公开(公告)号：US11593632B2

公开(公告)日：2023-02-28

申请号：US15439893

申请日：2017-02-22

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/62 ,  G06V10/44 ,  G06V10/75 ,  G06V20/40 ,  G06V20/52 ,  G06V30/10 ,  G06V30/194 ,  G06V40/16 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  G06N3/084 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.

公开(公告)号：US20210295164A1

公开(公告)日：2021-09-23

申请号：US17342921

申请日：2021-06-09

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06K9/66 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system applies trained models to compress binary code of an input image to a target codelength. For a set of binary codes representing the quantized coefficents of an input image, the DLBC system applies a first model that is trained to predict feature probabilities based on the context of each bit of the binary codes. The DLBC system compresses the binary code via adaptive arithmetic coding based on the determined probability of each bit. The compressed binary code represents a balance between a reconstruction quality of a reconstruction of the input image and a target compression ratio of the compressed binary code.