Patents by Inventor Lubomir Bourdev

Lubomir Bourdev 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: 20210295164
    Abstract: 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.
    Type: Application
    Filed: June 9, 2021
    Publication date: September 23, 2021
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 11100394
    Abstract: 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.
    Type: Grant
    Filed: July 1, 2020
    Date of Patent: August 24, 2021
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 11062211
    Abstract: 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.
    Type: Grant
    Filed: July 1, 2020
    Date of Patent: July 13, 2021
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 11003692
    Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first batch of content items to be clustered. A set of clusters can be generated by clustering respective binary hash codes for each content item in the first batch, wherein content items included in a cluster are visually similar to one another. A next batch of content items to be clustered can be obtained. One or more respective binary hash codes for the content items in the next batch can be assigned to a cluster in the set of clusters.
    Type: Grant
    Filed: December 28, 2015
    Date of Patent: May 11, 2021
    Assignee: Facebook, Inc.
    Inventors: Yunchao Gong, Marcin Pawlowski, Fei Yang, Lubomir Bourdev, Louis Dominic Brandy, Robert D. Fergus
  • Patent number: 10977553
    Abstract: 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.
    Type: Grant
    Filed: May 8, 2019
    Date of Patent: April 13, 2021
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 10860929
    Abstract: An encoder system trains a compression model that includes an autoencoder model and a frame extractor model. The encoding portion of the autoencoder is coupled to receive a set of target frames and a previous state tensor for the set of target frames and generate compressed code. The decoding portion of the autoencoder is coupled to receive the compressed code and the previous state tensor for the set of frames and generate a next state tensor for the set of target frames. The frame extractor model is coupled to receive the next state tensor and generate a set of reconstructed frames that correspond to the set of target frames by performing one or more operations on the state tensor. The state tensor for the set of frames includes information from frames of the video that can be used by the frame extractor to generate reconstructed frames.
    Type: Grant
    Filed: May 11, 2020
    Date of Patent: December 8, 2020
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander Anderson, Lubomir Bourdev
  • Publication number: 20200334535
    Abstract: 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.
    Type: Application
    Filed: July 1, 2020
    Publication date: October 22, 2020
    Inventors: Oren Rippel, Lubomir Bourdev
  • Publication number: 20200334534
    Abstract: 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.
    Type: Application
    Filed: July 1, 2020
    Publication date: October 22, 2020
    Inventors: Oren Rippel, Lubomir Bourdev
  • Publication number: 20200272903
    Abstract: An encoder system trains a compression model that includes an autoencoder model and a frame extractor model. The encoding portion of the autoencoder is coupled to receive a set of target frames and a previous state tensor for the set of target frames and generate compressed code. The decoding portion of the autoencoder is coupled to receive the compressed code and the previous state tensor for the set of frames and generate a next state tensor for the set of target frames. The frame extractor model is coupled to receive the next state tensor and generate a set of reconstructed frames that correspond to the set of target frames by performing one or more operations on the state tensor. The state tensor for the set of frames includes information from frames of the video that can be used by the frame extractor to generate reconstructed frames.
    Type: Application
    Filed: May 11, 2020
    Publication date: August 27, 2020
    Inventors: Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander Anderson, Lubomir Bourdev
  • Patent number: 10748062
    Abstract: 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.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: August 18, 2020
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 10685282
    Abstract: An encoder system trains a compression model that includes an autoencoder model and a frame extractor model. The encoding portion of the autoencoder is coupled to receive a set of target frames and a previous state tensor for the set of target frames and generate compressed code. The decoding portion of the autoencoder is coupled to receive the compressed code and the previous state tensor for the set of frames and generate a next state tensor for the set of target frames. The frame extractor model is coupled to receive the next state tensor and generate a set of reconstructed frames that correspond to the set of target frames by performing one or more operations on the state tensor. The state tensor for the set of frames includes information from frames of the video that can be used by the frame extractor to generate reconstructed frames.
    Type: Grant
    Filed: November 7, 2018
    Date of Patent: June 16, 2020
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander Anderson, Lubomir Bourdev
  • Patent number: 10594338
    Abstract: A compression system includes an encoder and a decoder. The encoder can be deployed by a sender system to encode a tensor for transmission to a receiver system, and the decoder can be deployed by the receiver system to decode and reconstruct the encoded tensor. The encoder receives a tensor for compression. The encoder also receives a quantization mask and probability data associated with the tensor. Each element of the tensor is quantized using an alphabet size allocated to that element by the quantization mask data. The encoder compresses the tensor by entropy coding each element using the probability data and alphabet size associated with the element. The decoder receives the quantization mask data, the probability data, and the compressed tensor data. The quantization mask and probabilities are used to entropy decode and subsequently reconstruct the tensor.
    Type: Grant
    Filed: March 18, 2019
    Date of Patent: March 17, 2020
    Assignee: WaveOne Inc.
    Inventors: Carissa Lew, Steven Branson, Oren Rippel, Sanjay Nair, Alexander Grant Anderson, Lubomir Bourdev
  • Patent number: 10572771
    Abstract: Systems, methods, and non-transitory computer-readable media can identify a set of regions corresponding to a geographical area. A collection of training images can be acquired. Each training image in the collection can be associated with one or more respective recognized objects and with a respective region in the set of regions. Histogram metrics for a plurality of object categories within each region in the set of regions can be determined based at least in part on the collection of training images. A neural network can be developed based at least in part on the histogram metrics for the plurality of object categories within each region in the set of regions and on the collection of training images.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: February 25, 2020
    Assignee: Facebook, Inc.
    Inventors: Kevin Dechau Tang, Lubomir Bourdev, Balamanohar Paluri, Robert D. Fergus
  • Patent number: 10565499
    Abstract: 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.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: February 18, 2020
    Assignee: WaveOne Inc.
    Inventors: Lubomir Bourdev, Carissa Lew, Sanjay Nair, Oren Rippel
  • Publication number: 20200034709
    Abstract: 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.
    Type: Application
    Filed: July 22, 2019
    Publication date: January 30, 2020
    Inventors: Oren Rippel, Lubomir Bourdev
  • Publication number: 20200036995
    Abstract: An encoder system trains a compression model that includes an autoencoder model and a frame extractor model. The encoding portion of the autoencoder is coupled to receive a set of target frames and a previous state tensor for the set of target frames and generate compressed code. The decoding portion of the autoencoder is coupled to receive the compressed code and the previous state tensor for the set of frames and generate a next state tensor for the set of target frames. The frame extractor model is coupled to receive the next state tensor and generate a set of reconstructed frames that correspond to the set of target frames by performing one or more operations on the state tensor. The state tensor for the set of frames includes information from frames of the video that can be used by the frame extractor to generate reconstructed frames.
    Type: Application
    Filed: November 7, 2018
    Publication date: January 30, 2020
    Inventors: Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander Anderson, Lubomir Bourdev
  • Publication number: 20190279053
    Abstract: A sample set of images is received. Each image in the sample set may be associated with one or more social cues. Correlation of each image in the sample set with an image class is scored based on the one or more social cues associated with the image. Based on the scoring, a training set of images to train a classifier is determined from the sample set. In an embodiment, an extent to which an evaluation set of images correlates with the image class is determined. The determination may comprise ranking a top scoring subset of the evaluation set of images.
    Type: Application
    Filed: November 15, 2018
    Publication date: September 12, 2019
    Inventors: Lubomir Bourdev, Balamanohar Paluri
  • Patent number: 10402722
    Abstract: A compression system trains a machine-learned encoder and decoder. The encoder can be deployed by a sender system to encode content for transmission to a receiver system, and the decoder can be deployed by the receiver system to decode the encoded content and reconstruct the original content. The encoder receives content and generates a tensor as a compact representation of the content. The content may be, for example, images, videos, or text. The decoder receives a tensor and generates a reconstructed version of the content. In one embodiment, the compression system trains one or more encoding components such that the encoder can adaptively encode different degrees of information for regions in the content that are associated with characteristic objects, such as human faces, texts, or buildings.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: September 3, 2019
    Assignee: WaveOne Inc.
    Inventors: Oren Rippel, Lubomir Bourdev, Carissa Lew, Sanjay Nair
  • Publication number: 20190266490
    Abstract: 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.
    Type: Application
    Filed: May 8, 2019
    Publication date: August 29, 2019
    Inventors: Oren Rippel, Lubomir Bourdev
  • Patent number: 10360498
    Abstract: Various embodiments of the present disclosure include systems, methods, and non-transitory computer storage media configured to identify a set of training content items, each of the set of training content items comprising video content. A category may be assigned to each of the set of training content items. A plurality of variations may be provided to the each of the set of training content items. A first content recognition module may be trained in an unsupervised process to associate the plurality of variations of the each of the set of training content items with the category assigned to the each of the set of training content items. A classification layer may be generated based on the training the first content recognition module in the unsupervised process. A second content recognition module may be trained in a supervised process based on the classification layer.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: July 23, 2019
    Assignee: Facebook, Inc.
    Inventors: Robert D. Fergus, Lubomir Bourdev, Balamanohar Paluri, Sainbayar Sukhbaatar