Patents by Inventor Zehan Wang
Zehan Wang 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).
-
Patent number: 10666962Abstract: Disclosed is method for training a plurality of visual processing algorithms for processing visual data. The method includes using a pre-processing hierarchical algorithm to process the visual data prior to encoding the visual data in visual data processing, and using a post-processing hierarchical algorithm to further process the visual data following decoding visual data in visual data processing. The encoding and decoding are performed with respect to a predetermined visual data codec and may be content specific.Type: GrantFiled: September 18, 2017Date of Patent: May 26, 2020Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Ferenc Huszar, Lucas Theis
-
Patent number: 10630996Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method including receiving at least a plurality of neighbouring sections of lower-quality visual data. A plurality of input sections from the received plurality of neighbouring sections of lower quality visual data are selected and features are extracted from those plurality of input sections of lower-quality visual data. A target section based on the extracted features from the plurality of input sections of lower-quality visual data is then enhanced.Type: GrantFiled: August 18, 2017Date of Patent: April 21, 2020Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10623775Abstract: A system (e.g., an auto-encoder system) includes an encoder, a decoder and a learning module. The encoder generates compressed video data using a lossy compression algorithm, the lossy compression algorithm being implemented using a trained neural network with at least one convolution, generate at least one first parameter based on the compressed video data, and communicate the compressed video data and the model to at least one device configured to decode the compressed video data using an inverse algorithm based on the lossy compression algorithm. The decoder generates decoded video data based on the compressed video data using the inverse algorithm and the model, and generate at least one second parameter based on the decoded video data. The learning module trains the model using the at least one first parameter and the at least one second parameter.Type: GrantFiled: November 6, 2017Date of Patent: April 14, 2020Assignee: Twitter, Inc.Inventors: Lucas Theis, Ferenc Huszar, Zehan Wang, Wenzhe Shi
-
Patent number: 10623756Abstract: A method for enhancing lower-quality visual data using hierarchical algorithms, the method comprising the steps of: receiving one or more sections of lower-quality visual data; applying a hierarchical algorithm to the one or more sections of lower-quality visual data to enhance the one or more sections of lower-quality visual data to one or more sections of higher-quality visual data, wherein the hierarchical algorithm was developed using a learned approach; and outputting the one or more sections of higher-quality visual data.Type: GrantFiled: August 18, 2017Date of Patent: April 14, 2020Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10602163Abstract: The present disclosure relates to analysing input data, prior to encoding, using one or more hierarchical algorithms. According to a first aspect, there is provided a method for producing output data using one or more input data and one or more hierarchical algorithms, comprising the steps of applying the hierarchical algorithm to the one or more input data; and producing output data to be used by an encoder; wherein one of the one or more input data is uncompressed; and wherein the output data is used to modify a decision making process associated with the encoder.Type: GrantFiled: December 28, 2017Date of Patent: March 24, 2020Assignee: Magic Pony Technology LimitedInventors: Sebastiaan Van Leuven, Zehan Wang, Robert David Bishop
-
Patent number: 10582205Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method comprises receiving at least one section of lower-quality visual data; and extracting a subset of features, from the at least one section of lower-quality visual data. A plurality of layers of reduced-dimension visual data from the extracted features are formed and enhanced to form at least one section of higher-quality visual data. The at least one section of higher-quality visual data corresponds to the at least one section of lower-quality visual data received.Type: GrantFiled: August 18, 2017Date of Patent: March 3, 2020Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10552977Abstract: Systems and methods generate a face-swapped image from a target image using a convolutional neural network trained to apply a source identity to the expression and pose of the target image. The convolutional neural network produces face-swapped images fast enough to transform a video stream. An example method includes aligning the face portion of a target image from an original view to a reference view to generate a target face and generating a swapped face by changing the target face to that of a source identity using a convolutional neural network trained to minimize loss of content from the target face and style from the source identity. The method also includes realigning the swapped face from the reference view to the original view and generating a swapped image by stitching the realigned swapped face with the remaining portion of the target image.Type: GrantFiled: April 18, 2017Date of Patent: February 4, 2020Assignee: Twitter, Inc.Inventors: Lucas Theis, Iryna Korshunova, Wenzhe Shi, Zehan Wang
-
Patent number: 10547858Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method comprising receiving at least a plurality of neighbouring sections of lower-quality visual data. A plurality of input sections from the received plurality of neighbouring sections of lower quality visual data are selected and features are extracted from those plurality of input sections of lower-quality visual data. A target section based on the extracted features from the plurality of input sections of lower-quality visual data is then enhanced.Type: GrantFiled: August 17, 2017Date of Patent: January 28, 2020Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10523955Abstract: A method for enhancing at least a section of lower-quality visual data, the method comprising at least a section of the lower-quality visual data being received. A hierarchical algorithm is then selected from a plurality of hierarchical algorithms, wherein the step of selection is based on a predetermined metric and wherein the hierarchical algorithms were developed using a learned approach and at least one of the hierarchical algorithms is operable to increase the quality of the lower-quality visual data. The selected hierarchical algorithm is then used to increase the quality of the lower-quality visual data to create a higher-quality visual data.Type: GrantFiled: August 17, 2017Date of Patent: December 31, 2019Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10516890Abstract: A method for training learned hierarchical algorithms, the method comprising the steps of receiving input data and generating metrics from the input data. At least one hierarchical algorithm is then selected from a plurality of predetermined hierarchical algorithms based on comparing the generated metrics from the input data and like metrics for each of the plurality of predetermined hierarchical algorithms. The selected hierarchical algorithm is developed based on the input data and the developed hierarchical algorithm is outputted.Type: GrantFiled: August 18, 2017Date of Patent: December 24, 2019Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Patent number: 10499069Abstract: A method for enhancing visual data when communicating visual data over a network from a first node to a second node. The method at the first node comprises developing at least one modified hierarchical algorithm from a known hierarchical algorithm operable to substantially recreate at least one section of higher-quality visual data. References to one or more known hierarchical algorithms from which the modified hierarchical algorithms were developed are transmitted to the second node along with one or more modifications to the one or more known hierarchical algorithms operable to reproduce the one or more modified hierarchical algorithms from the known hierarchical algorithms. The second node is able to recreate substantially the higher-quality video using the modified hierarchical algorithm.Type: GrantFiled: August 18, 2017Date of Patent: December 3, 2019Assignee: Magic Pony Technology LimitedInventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Publication number: 20180240031Abstract: Systems and methods provide a deep neural network trained via active learning. An example method includes generating, from a set of labeled objects, a plurality of differing training sets, assigning each of the plurality of training sets to a respective deep neural network in a committee of networks, and initializing each of the deep neural networks in the committee by training the deep neural network using the respective assigned training set. The method further includes iteratively training the deep neural networks in the committee until convergence and using one of the deep neural networks to make predictions for unlabeled objects. The training may include identifying unlabeled objects with highest diversity in predictions from the plurality of deep neural networks, obtaining a respective label for each identified unlabeled object, and retraining the deep neural networks with the respective labels for the objects.Type: ApplicationFiled: January 22, 2018Publication date: August 23, 2018Inventors: Ferenc Huszar, Pietro Berkes, Zehan Wang
-
Publication number: 20180242017Abstract: A method includes receiving one of a first encoded video data representing an 2D representation of a frame of omnidirectional video, and a second encoded video data representing a plurality of images each representing a section of the frame of omnidirectional video, receiving an indication of a view point on the omnidirectional video, selecting a portion of the omnidirectional video based on the view point, encoding the selected portion of the omnidirectional video, and communicating the encoded omnidirectional video in response to receiving the indication of the view point on the omnidirectional video.Type: ApplicationFiled: December 31, 2017Publication date: August 23, 2018Inventors: Sebastiaan Van Leuven, Zehan Wang
-
Publication number: 20180144526Abstract: A method for developing visual data using source data, target data, and a hierarchical algorithm. According to a first aspect, there is provided a method for developing visual data from source data, target data and using a hierarchical algorithm, the method comprising the steps of: determining an alignment between the target data and the source data; and producing the visual data by transferring one or more features of the source data onto one or more features of the target data; wherein, the visual data is produced after the step of determining the alignment between the target data and the source data; and wherein the visual data is produced using the hierarchical algorithm.Type: ApplicationFiled: December 28, 2017Publication date: May 24, 2018Inventors: Lucas Theis, Zehan Wang, Robert David Bishop
-
Publication number: 20180139458Abstract: Methods and systems for optimising the quality of visual data. Specifically, methods and systems for preserving visual information during compression and decompression. An example method for optimising visual data includes using a pre-processing hierarchical algorithm to optimise visual data prior to encoding the visual data in visual data processing; and using a post-processing hierarchical algorithm to enhance visual data following decoding visual data in visual data processing.Type: ApplicationFiled: December 27, 2017Publication date: May 17, 2018Inventors: Zehan Wang, Robert David Bishop, Ferenc Huszar, Lucas Theis
-
Publication number: 20180130178Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method comprises receiving at least one section of lower-quality visual data; and extracting a subset of features, from the at least one section of lower-quality visual data. A plurality of layers of reduced-dimension visual data from the extracted features are formed and enhanced to form at least one section of higher-quality visual data. The at least one section of higher-quality visual data corresponds to the at least one section of lower-quality visual data received.Type: ApplicationFiled: August 18, 2017Publication date: May 10, 2018Inventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Publication number: 20180130179Abstract: A method for enhancing lower-quality visual data using hierarchical algorithms, the method comprising the steps of: receiving one or more sections of lower-quality visual data; applying a hierarchical algorithm to the one or more sections of lower-quality visual data to enhance the one or more sections of lower-quality visual data to one or more sections of higher-quality visual data, wherein the hierarchical algorithm was developed using a learned approach; and outputting the one or more sections of higher-quality visual data.Type: ApplicationFiled: August 18, 2017Publication date: May 10, 2018Inventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Publication number: 20180129918Abstract: A method for training learned hierarchical algorithms, the method comprising the steps of receiving input data and generating metrics from the input data. At least one hierarchical algorithm is then selected from a plurality of predetermined hierarchical algorithms based on comparing the generated metrics from the input data and like metrics for each of the plurality of predetermined hierarchical algorithms. The selected hierarchical algorithm is developed based on the input data and the developed hierarchical algorithm is outputted.Type: ApplicationFiled: August 18, 2017Publication date: May 10, 2018Inventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz
-
Publication number: 20180131953Abstract: Disclosed is method for training a plurality of visual processing algorithms for processing visual data. The method includes using a pre-processing hierarchical algorithm to process the visual data prior to encoding the visual data in visual data processing, and using a post-processing hierarchical algorithm to further process the visual data following decoding visual data in visual data processing. The encoding and decoding are performed with respect to a predetermined visual data codec and may be content specific.Type: ApplicationFiled: September 18, 2017Publication date: May 10, 2018Inventors: Zehan Wang, Robert David Bishop, Ferenc Huszar, Lucas Theis
-
Publication number: 20180130180Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method including receiving at least a plurality of neighbouring sections of lower-quality visual data. A plurality of input sections from the received plurality of neighbouring sections of lower quality visual data are selected and features are extracted from those plurality of input sections of lower-quality visual data. A target section based on the extracted features from the plurality of input sections of lower-quality visual data is then enhanced.Type: ApplicationFiled: August 18, 2017Publication date: May 10, 2018Inventors: Zehan Wang, Robert David Bishop, Wenzhe Shi, Jose Caballero, Andrew Peter Aitken, Johannes Totz