Patents by Inventor Noam Elron

Noam Elron 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: 12361515
    Abstract: A method, system, and article is directed to real-time super-resolution image processing using neural networks.
    Type: Grant
    Filed: March 26, 2021
    Date of Patent: July 15, 2025
    Assignee: Intel Corporation
    Inventors: Noam Elron, Alexander Itskovich, Shahar S Yuval, Noam Levy
  • Publication number: 20250191142
    Abstract: Systems and methods for providing a temporal noise reducer (TNR) architecture that improves TNR performance by adjusting for lighting differences between image frames. Temporal noise reduction is a core feature of a video processing pipeline, where TNR can be used to decrease noise in video streams. Some TNRs compensate for the motion of objects between frames, but lighting changes can also lead to additional noise. As an object's position moves from frame to frame, the lighting of the object may change. A lightweight tone-mapping and color-correction operator is added to the TNR feedback loop, matching the radiometric properties of a TNR reference frame to the radiometric properties of the current frame to compensate for radiometric differences, thereby increasing the effectiveness of TNR in handling incremental lighting changes and speeding up its response to abrupt lighting changes.
    Type: Application
    Filed: February 19, 2025
    Publication date: June 12, 2025
    Applicant: Intel Corporation
    Inventor: Noam Elron
  • Publication number: 20250005765
    Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to process images using segmentation. An example apparatus includes interface circuitry, machine readable instructions, and programmable circuitry to at least one of instantiate or execute the machine readable instructions to generate a scaled frame from an input video frame, segment, with a neural network, the scaled frame to generate a scaled segmentation map based on the scaled frame, the scaled segmentation map to associate pixels of the scaled frame with ones of a plurality of segments in the scaled frame, and generate an output video frame based on the input video frame and an upscaled version of the scaled segmentation map.
    Type: Application
    Filed: June 27, 2023
    Publication date: January 2, 2025
    Inventors: Dmitry Rudoy, Rakefet Kol, Noam Elron, Noam Levy
  • Publication number: 20250005709
    Abstract: Example methods, apparatus, systems, and articles directed to real-time super-resolution image processing using neural networks are disclosed. Example apparatus disclosed herein cause a neural network to process an input frame of input video, the input video having a first resolution, the neural network trained to upscale the input frame to a second resolution, the neural network trained to reduce a presence of one or more types of image imperfections in the input frame. Disclosed example apparatus also obtain, from the neural network, an output frame at the second resolution. Disclosed example apparatus further cause the output frame to be presented as part of an output video at the second resolution.
    Type: Application
    Filed: September 11, 2024
    Publication date: January 2, 2025
    Inventors: Noam Elron, Alexander Itskovich, Shahar S Yuval, Noam Levy
  • Publication number: 20240265580
    Abstract: A high dynamic range video frame can be generated from images captured using different exposure times. The merging of images may use a parameter, exposure time ratio, to combine pixel values of images to form a merged video frame. The quality of the merged video frame can depend on accuracy of the exposure time ratio. In some scenarios, the exposure time ratio is unknown or the reported information about the exposure time ratio from an auto-exposure controller is inaccurate. Using an inaccurate exposure time ratio to merge images would result in undesirable artifacts in the merged video frame. To address this issue, a self-calibrating technique may be implemented to derive the exposure time ratio based on the images themselves.
    Type: Application
    Filed: March 20, 2024
    Publication date: August 8, 2024
    Inventor: Noam Elron
  • Publication number: 20240249392
    Abstract: A high-level understanding of the scene captured by a camera allows for the use of scene-level understanding in the processing of the captured image. A downscaled image of a captured scene is generated and used as a basis for artificial intelligence analysis before the full image of the captured scene is processed. The downscaled image is generated concurrently with the capturing of the raw image at the image sensor and before full image signal processor (ISP) processing. Neural networks and other AI algorithms can be applied directly to the downscaled image to perform high-level understanding using minimal resources. The processing of the full scale captured image can be adapted to specific scenarios based on the understanding rather than undergoing all-purpose processing. The high-level understanding is provided to the full image processing pipe for enhancements in image quality, video conferencing, face detection, and other user experiences.
    Type: Application
    Filed: February 21, 2024
    Publication date: July 25, 2024
    Applicant: Intel Corporation
    Inventors: Dmitry Rudoy, Rakefet Kol, Noam Elron, Noam Levy
  • Publication number: 20240046427
    Abstract: An unsupervised technique for training a deep learning based temporal noise reducer on unlabeled real-world data. The unsupervised technique can also be used to calibrate the free parameters of a TNR based on algorithmic principles. The training is based on actual real-world video (which may include noise), and not based on video containing artificial or added noise. Using the unsupervised technique to train a TNR allows the TNR to be tailored to the noise statistics of the use-case, resulting in the provision of high quality video with minimal resources. The TNR can be based on an uncalibrated TNR's output in time-reverse, as well as the uncalibrated TNR's output in time-forward. The frames used for both the time-forward output and the time-reversed output can be frames from the past. The TNR is calibrated to minimize the difference between its time-forward output and its time-reversed output.
    Type: Application
    Filed: October 13, 2023
    Publication date: February 8, 2024
    Applicant: Intel Corporation
    Inventor: Noam Elron
  • Patent number: 11823352
    Abstract: An example apparatus for video imaging includes a feature estimator to calculate a local value of a feature for averaging in a compressed set of features of a current frame. The apparatus also includes a validator to calculate a validity map comprising a weight for frame-wide averaging based on the compressed current frame. The apparatus further includes a vector generator to generate a state vector based on the local value of the feature and the weight. The apparatus further includes a relevance calculator to calculate a relevance to local processing for each coordinate in a restored state vector associated with a previous frame. The apparatus further includes a vector modulator to multiply the restored state vector by the relevance feature to generate a set of output features.
    Type: Grant
    Filed: February 13, 2020
    Date of Patent: November 21, 2023
    Assignee: INTEL CORPORATION
    Inventor: Noam Elron
  • Patent number: 11688070
    Abstract: An example apparatus for video frame segmentation includes a receiver to receive a current video frame to be segmented. The apparatus also includes a segmenting neural network to receive a previous mask including a segmentation mask corresponding to a previous frame and generate a segmentation mask for the current frame based on the previous mask and the video frame.
    Type: Grant
    Filed: June 25, 2020
    Date of Patent: June 27, 2023
    Assignee: Intel Corporation
    Inventors: Amir Goren, Noam Elron, Noam Levy
  • Publication number: 20220092400
    Abstract: A method, system, and article of highly efficient neural network video image processing uses temporal correlations.
    Type: Application
    Filed: December 6, 2021
    Publication date: March 24, 2022
    Applicant: Intel Corporation
    Inventors: Noam Elron, Ben Berlin, Dmitry Rudoy, Amir Goren, Noam Levy
  • Publication number: 20210233210
    Abstract: A method, system, and article is directed to real-time super-resolution image processing using neural networks.
    Type: Application
    Filed: March 26, 2021
    Publication date: July 29, 2021
    Applicant: Intel Corporation
    Inventors: Noam Elron, Alexander Itskovich, Shahar S Yuval, Noam Levy
  • Publication number: 20200327334
    Abstract: An example apparatus for video frame segmentation includes a receiver to receive a current video frame to be segmented. The apparatus also includes a segmenting neural network to receive a previous mask including a segmentation mask corresponding to a previous frame and generate a segmentation mask for the current frame based on the previous mask and the video frame.
    Type: Application
    Filed: June 25, 2020
    Publication date: October 15, 2020
    Applicant: INTEL CORPORATION
    Inventors: Amir Goren, Noam Elron, Noam Levy
  • Patent number: 10735769
    Abstract: Techniques related to temporal noise reduction in captured video are discussed. Such techniques include performing motion estimation on a portion of a downsampled current frame performed during the downsampling of the current frame, replacing one or more of the resultant motion vectors based on confidence scores of the resultant motion vector, and blending the current frame and a temporally previous frame to generate a temporally filtered current frame. The temporally filtered current frame may be displayed to a user and/or encoded to generate a bitstream.
    Type: Grant
    Filed: September 25, 2018
    Date of Patent: August 4, 2020
    Assignee: Intel Corporation
    Inventors: Noam Levy, Liron Lvov, Noam Elron, Oskar Pelc, Shahar S. Yuval
  • Publication number: 20200184606
    Abstract: An example apparatus for video imaging includes a feature estimator to calculate a local value of a feature for averaging in a compressed set of features of a current frame. The apparatus also includes a validator to calculate a validity map comprising a weight for frame-wide averaging based on the compressed current frame. The apparatus further includes a vector generator to generate a state vector based on the local value of the feature and the weight. The apparatus further includes a relevance calculator to calculate a relevance to local processing for each coordinate in a restored state vector associated with a previous frame. The apparatus further includes a vector modulator to multiply the restored state vector by the relevance feature to generate a set of output features.
    Type: Application
    Filed: February 13, 2020
    Publication date: June 11, 2020
    Applicant: INTEL CORPORATION
    Inventor: Noam Elron
  • Publication number: 20190045223
    Abstract: Techniques related to temporal noise reduction in captured video are discussed. Such techniques include performing motion estimation on a portion of a downsampled current frame performed during the downsampling of the current frame, replacing one or more of the resultant motion vectors based on confidence scores of the resultant motion vector, and blending the current frame and a temporally previous frame to generate a temporally filtered current frame. The temporally filtered current frame may be displayed to a user and/or encoded to generate a bitstream.
    Type: Application
    Filed: September 25, 2018
    Publication date: February 7, 2019
    Applicant: Intel Corporation
    Inventors: Noam Levy, Liron Lvov, Noam Elron, Oskar Pelc, Shahar S. Yuval