Patents by Inventor Alireza Zare

Alireza Zare 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: 12108050
    Abstract: The embodiments relate to a method for encoding and a decoding, and apparatuses for the same. The method for encoding comprises receiving a block of a video frame for encoding (1510); making a decision on whether or not a learning-based model is to be applied as a processing step for encoding the block (1520); applying the learning-based model for said input block according to the decision, where the learning-based model has been selectively fine-tuned according to information relating to activation of the learning-based model of previously-decoded blocks (1530); encoding a signal corresponding to the decision on usage of the learning-based model into a bitstream (1540); and encoding the block into a bitstream with an information whether the block is to be used for finetuning (1550).
    Type: Grant
    Filed: February 12, 2021
    Date of Patent: October 1, 2024
    Assignee: Nokia Technologies Oy
    Inventors: Jani Lainema, Francesco Cricri, Emre Baris Aksu, Alireza Zare, Miska Matias Hannuksela
  • Publication number: 20240291981
    Abstract: A method comprising: dividing pictures of one or more input picture sequences into a plurality of subpictures (1000); encoding each of the subpictures into a plurality of subpicture versions having different quality and/or resolution (1002); partitioning the plurality of subpicture versions into one or more subpicture groups (1004); and allocating a range of adaptive loop filter parameter set identifiers coefficients for each of said subpicture groups (1006).
    Type: Application
    Filed: August 31, 2022
    Publication date: August 29, 2024
    Inventors: Alireza ZARE, Alireza AMINLOU, Miska Matias HANNUKSELA
  • Publication number: 20230110503
    Abstract: The embodiments relate to method for encoding and decoding, wherein the method for encoding comprises receiving an input block of a video frame for encoding; applying at least a learning-based model (702) for said input block as a processing step for encoding the block; combining (703) an output of a learning-based model with one or more data sources (712, 713) by a combination process; encoding block to a bitstream (40); using a result of the combination process as additional input for the learning-based model for encoding a subsequent block; and encoding to a bitstream combination information (720) used in the combination process, said combination information comprising at least one or more combination parameters. The embodiments also relate to technical equipment for implementing the methods.
    Type: Application
    Filed: February 4, 2021
    Publication date: April 13, 2023
    Inventors: Jani LAINEMA, Emre Baris AKSU, Miska Matias HANNUKSELA, Alireza ZARE, Francesco CRICRI
  • Publication number: 20230062752
    Abstract: The embodiments relate to a method for encoding and a decoding, and apparatuses for the same. The method for encoding comprises receiving a block of a video frame for encoding (1510); making a decision on whether or not a learning-based model is to be applied as a processing step for encoding the block (1520); applying the learning-based model for said input block according to the decision, where the learning-based model has been selectively fine-tuned according to information relating to activation of the learning-based model of previously-decoded blocks (1530); encoding a signal corresponding to the decision on usage of the learning-based model into a bitstream (1540); and encoding the block into a bitstream with an information whether the block is to be used for finetuning (1550).
    Type: Application
    Filed: February 12, 2021
    Publication date: March 2, 2023
    Inventors: Jani LAINEMA, Francesco CRICRI, Emre Baris AKSU, Alireza ZARE, Miska Matias HANNUKSELA
  • Patent number: 11341688
    Abstract: Optimization of a neural network, for example in a video codec at the decoder side, may be guided to limit overfitting. The encoder may encode video(s) with different qualities for different frames in the video. Low-quality frames may be used as both input and ground-truth during optimization. High-quality frames may be used to optimize the neural network so that higher-quality versions of lower-quality inputs may be predicted. The neural network may be trained to make such predictions by making a prediction based on a constructed low-quality input for which the corresponding high-quality version is known, comparing the prediction to the high-quality version, and fine-tuning the neural network to improve its ability to predict a high-quality version of a low-quality input. To limit overfitting, the neural network may be concurrently or in an alternating fashion trained with low-quality input for which a higher-quality version of the low-quality input is known.
    Type: Grant
    Filed: September 30, 2020
    Date of Patent: May 24, 2022
    Assignee: Nokia Technologies Oy
    Inventors: Alireza Zare, Francesco Cricri, Yat Hong Lam, Miska Matias Hannuksela, Jani Olavi Lainema
  • Patent number: 11323723
    Abstract: A method comprising obtaining a full-picture track or bitstream including a motion-constrained tile set; and constructing a full-picture-compliant tile set track or bitstream on the basis of the motion-constrained tile set or generating instructions to construct a full-picture-compliant tile set track or bitstream on the basis of the motion-constrained tile set.
    Type: Grant
    Filed: February 14, 2017
    Date of Patent: May 3, 2022
    Assignee: Nokia Technologies Oy
    Inventors: Miska Hannuksela, Alireza Aminlou, Alireza Zare
  • Publication number: 20210227231
    Abstract: A method comprising obtaining a full-picture track or bitstream including a motion-constrained tile set; and constructing a full-picture-compliant tile set track or bitstream on the basis of the motion-constrained tile set or generating instructions to construct a full-picture-compliant tile set track or bitstream on the basis of the motion-constrained tile set.
    Type: Application
    Filed: February 14, 2017
    Publication date: July 22, 2021
    Inventors: Miska Hannuksela, Alireza Aminlou, Alireza Zare
  • Publication number: 20210104076
    Abstract: Optimization of a neural network, for example in a video codec at the decoder side, may be guided to limit overfitting. The encoder may encode video(s) with different qualities for different frames in the video. Low-quality frames may be used as both input and ground-truth during optimization. High-quality frames may be used to optimize the neural network so that higher-quality versions of lower-quality inputs may be predicted. The neural network may be trained to make such predictions by making a prediction based on a constructed low-quality input for which the corresponding high-quality version is known, comparing the prediction to the high-quality version, and fine-tuning the neural network to improve its ability to predict a high-quality version of a low-quality input. To limit overfitting, the neural network may be concurrently or in an alternating fashion trained with low-quality input for which a higher-quality version of the low-quality input is known.
    Type: Application
    Filed: September 30, 2020
    Publication date: April 8, 2021
    Inventors: Alireza Zare, Francesco Cricri, Yat Hong Lam, Miska Matias Hannuksela, Jani Olavi Lainema