Patents by Inventor Haoyu Ren

Haoyu Ren 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: 20250069247
    Abstract: Methods and systems for performing video prediction, including obtaining an input frame from among a plurality of frames included in an input video; extracting a first feature map by providing the input frame to a first plurality of feature extraction layers and a first strided convolutional layer included in an encoder; providing the first feature map and at least one neighboring first feature map corresponding to at least one neighboring frame to a first fusion module included in the encoder; fusing the first feature map with the at least one neighboring first feature map to generate a fused first feature map using the first fusion module; generating a prediction corresponding to the input frame based on the fused first feature map using a decoder; and performing a video prediction task using the prediction.
    Type: Application
    Filed: November 11, 2024
    Publication date: February 27, 2025
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Haoyu REN, Mostafa EL-KHAMY, Jungwon LEE, Hai SU, Qingfeng LIU
  • Publication number: 20240346673
    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.
    Type: Application
    Filed: May 28, 2024
    Publication date: October 17, 2024
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
  • Patent number: 12026627
    Abstract: A computer vision (CV) training system, includes: a supervised learning system to estimate a supervision output from one or more input images according to a target CV application, and to determine a supervised loss according to the supervision output and a ground-truth of the supervision output; an unsupervised learning system to determine an unsupervised loss according to the supervision output and the one or more input images; a weakly supervised learning system to determine a weakly supervised loss according to the supervision output and a weak label corresponding to the one or more input images; and a joint optimizer to concurrently optimize the supervised loss, the unsupervised loss, and the weakly supervised loss.
    Type: Grant
    Filed: August 17, 2022
    Date of Patent: July 2, 2024
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee, Aman Raj
  • Patent number: 11995856
    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.
    Type: Grant
    Filed: December 13, 2022
    Date of Patent: May 28, 2024
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Haoyu Ren, Mostafa El Khamy, Jungwon Lee
  • Patent number: 11900234
    Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: February 13, 2024
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
  • Patent number: 11861859
    Abstract: Method and systems are provided for robust disparity estimation based on cost-volume attention. A method includes extracting first feature maps from left images captured by a first camera; extracting second feature maps from right images captured by a second camera; calculating a matching cost based on a comparison of the first and second feature maps to generate a cost volume; generating an attention-aware cost volume from the generated cost volume; and aggregating the attention-aware cost volume to generate an output disparity.
    Type: Grant
    Filed: December 22, 2020
    Date of Patent: January 2, 2024
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Mostafa El-Khamy, Jungwon Lee, Haoyu Ren
  • Patent number: 11790489
    Abstract: A method and apparatus are provided. The method includes generating a dataset for real-world super resolution (SR), training a first generative adversarial network (GAN), training a second GAN, and fusing an output of the first GAN and an output of the second GAN.
    Type: Grant
    Filed: December 24, 2020
    Date of Patent: October 17, 2023
    Inventors: Haoyu Ren, Amin Kheradmand, Mostafa El-Khamy, Shuangquan Wang, Dongwoon Bai, Jungwon Lee
  • Patent number: 11699070
    Abstract: A method and apparatus for providing a rotational invariant neural network is herein disclosed. According to one embodiment, a method includes receiving a first input of an image in a first orientation and training a kernel to be symmetric such that an output corresponding to the first input is the same as an output corresponding to a second input of the image in a second orientation.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: July 11, 2023
    Inventors: Mostafa El-Khamy, Jungwon Lee, Yoo Jin Choi, Haoyu Ren
  • Patent number: 11694305
    Abstract: In a method for super resolution imaging, the method includes: receiving, by a processor, a low resolution image; generating, by the processor, an intermediate high resolution image having an improved resolution compared to the low resolution image; generating, by the processor, a final high resolution image based on the intermediate high resolution image and the low resolution image; and transmitting, by the processor, the final high resolution image to a display device for display thereby.
    Type: Grant
    Filed: April 6, 2021
    Date of Patent: July 4, 2023
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Mostafa El-Khamy, Jungwon Lee, Haoyu Ren
  • Publication number: 20230116893
    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.
    Type: Application
    Filed: December 13, 2022
    Publication date: April 13, 2023
    Inventors: Haoyu Ren, Mostafa El Khamy, Jungwon Lee
  • Patent number: 11599979
    Abstract: A method and an apparatus are provided. The method includes receiving a video with a first plurality of frames having a first resolution; generating a plurality of warped frames from the first plurality of frames based on a first type of motion compensation; generating a second plurality of frames having a second resolution, wherein the second resolution is of higher resolution than the first resolution, wherein each of the second plurality of frames having the second resolution is derived from a subset of the plurality of warped frames using a convolutional network; and generating a third plurality of frames having the second resolution based on a second type of motion compensation, wherein each of the third plurality of frames having the second resolution is derived from a fusing a subset of the second plurality of frames.
    Type: Grant
    Filed: May 29, 2020
    Date of Patent: March 7, 2023
    Inventors: Mostafa El-Khamy, Haoyu Ren, Jungwon Lee
  • Patent number: 11527005
    Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.
    Type: Grant
    Filed: April 6, 2020
    Date of Patent: December 13, 2022
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
  • Publication number: 20220391632
    Abstract: A computer vision (CV) training system, includes: a supervised learning system to estimate a supervision output from one or more input images according to a target CV application, and to determine a supervised loss according to the supervision output and a ground-truth of the supervision output; an unsupervised learning system to determine an unsupervised loss according to the supervision output and the one or more input images; a weakly supervised learning system to determine a weakly supervised loss according to the supervision output and a weak label corresponding to the one or more input images; and a joint optimizer to concurrently optimize the supervised loss, the unsupervised loss, and the weakly supervised loss.
    Type: Application
    Filed: August 17, 2022
    Publication date: December 8, 2022
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee, Aman Raj
  • Publication number: 20220383066
    Abstract: Various embodiments of the teachings herein include methods for amending or adding machine learning capabilities to an automation device in an automation system. The method may include: 1) providing a capability model of the automation device semantically representing capabilities of the device; 2) providing a machine learning model for semantically representing a machine learning functionality and including a semantic model of a neural network; 3) deploying the machine learning model within the automation device; 4) interpreting a semantic part of the machine learning model using a semantic reasoner and matching requirements of the machine learning model with device capabilities inferred by the capability model; and 5) executing the machine learning functionalities on the automation device.
    Type: Application
    Filed: July 18, 2022
    Publication date: December 1, 2022
    Applicant: Siemens Aktiengesellschaft
    Inventors: Darko Anicic, Haoyu Ren, Thomas Runkler
  • Publication number: 20220300819
    Abstract: Apparatuses and methods of manufacturing same, systems, and methods are described. In one aspect, a method includes generating a convolutional neural network (CNN) by training a CNN having a plurality of convolutional layers, and performing cascade training on the trained CNN. The cascade training includes an iterative process of a plurality of stages, in which each stage includes inserting a residual block (ResBlock) and training the CNN with the inserted ResBlock.
    Type: Application
    Filed: May 27, 2022
    Publication date: September 22, 2022
    Inventors: Haoyu REN, Mostafa EL-KHAMY, Jungwon LEE
  • Patent number: 11429805
    Abstract: A computer vision (CV) training system, includes: a supervised learning system to estimate a supervision output from one or more input images according to a target CV application, and to determine a supervised loss according to the supervision output and a ground-truth of the supervision output; an unsupervised learning system to determine an unsupervised loss according to the supervision output and the one or more input images; a weakly supervised learning system to determine a weakly supervised loss according to the supervision output and a weak label corresponding to the one or more input images; and a joint optimizer to concurrently optimize the supervised loss, the unsupervised loss, and the weakly supervised loss.
    Type: Grant
    Filed: May 11, 2020
    Date of Patent: August 30, 2022
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee, Aman Raj
  • Patent number: 11354577
    Abstract: Apparatuses and methods of manufacturing same, systems, and methods are described. In one aspect, a method includes generating a convolutional neural network (CNN) by training a CNN having three or more convolutional layers, and performing cascade training on the trained CNN. The cascade training includes an iterative process of one or more stages, in which each stage includes inserting a residual block (ResBlock) including at least two additional convolutional layers and training the CNN with the inserted ResBlock.
    Type: Grant
    Filed: September 21, 2018
    Date of Patent: June 7, 2022
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
  • Publication number: 20220051426
    Abstract: Method and systems are provided for robust disparity estimation based on cost-volume attention. A method includes extracting first feature maps from left images captured by a first camera; extracting second feature maps from right images captured by a second camera; calculating a matching cost based on a comparison of the first and second feature maps to generate a cost volume; generating an attention-aware cost volume from the generated cost volume; and aggregating the attention-aware cost volume to generate an output disparity.
    Type: Application
    Filed: December 22, 2020
    Publication date: February 17, 2022
    Inventors: Mostafa EL-KHAMY, Jungwon LEE, Haoyu REN
  • Publication number: 20210312591
    Abstract: A method and apparatus are provided. The method includes generating a dataset for real-world super resolution (SR), training a first generative adversarial network (GAN), training a second GAN, and fusing an output of the first GAN and an output of the second GAN.
    Type: Application
    Filed: December 24, 2020
    Publication date: October 7, 2021
    Inventors: Haoyu REN, Amin KHERADMAND, Mostafa EL-KHAMY, Shuangquan WANG, Dongwoon BAI, Jungwon LEE
  • Patent number: 11094072
    Abstract: A method and system for determining depth information of an image are herein provided. According to one embodiment, the method includes receiving an image input, classifying the input image into a depth range of a plurality of depth ranges, and determining a depth map of the image by applying depth estimation based on the depth range into which the input image is classified.
    Type: Grant
    Filed: September 18, 2019
    Date of Patent: August 17, 2021
    Inventors: Haoyu Ren, Mostafa El-Khamy, Jungwon Lee