Patents by Inventor Stephan KALTENSTADLER

Stephan KALTENSTADLER 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: 20250056040
    Abstract: An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to: resample a second template of samples neighboring the current block, so as to conform with the first template so as to obtain a resampled template; apply the resampled template of samples onto the neural network so as to obtain a preliminary intra-prediction signal; and resample the preliminary intra-prediction signal so as to conform with the current block so as to obtain the intra-prediction signal for the current block.
    Type: Application
    Filed: October 23, 2024
    Publication date: February 13, 2025
    Inventors: Jonathan PFAFF, Philipp HELLE, Philipp MERKLE, Björn STALLENBERGER, Mischa SIEKMANN, Martin WINKEN, Adam WIECKOWSKI, Wojciech SAMEK, Stephan KALTENSTADLER, Heiko SCHWARZ, Detlev MARPE, Thomas WIEGAND
  • Patent number: 12160606
    Abstract: An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to: resample a second template of samples neighboring the current block, so as to conform with the first template so as to obtain a resampled template; apply the resampled template of samples onto the neural network so as to obtain a preliminary intra-prediction signal; and resample the preliminary intra-prediction signal so as to conform with the current block so as to obtain the intra-prediction signal for the current block.
    Type: Grant
    Filed: January 9, 2023
    Date of Patent: December 3, 2024
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung, e.V.
    Inventors: Jonathan Pfaff, Philipp Helle, Philipp Merkle, Björn Stallenberger, Mischa Siekmann, Martin Winken, Adam Wieckowski, Wojciech Samek, Stephan Kaltenstadler, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  • Publication number: 20240137500
    Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.
    Type: Application
    Filed: December 19, 2023
    Publication date: April 25, 2024
    Inventors: Jonathan PFAFF, Philipp HELLE, Dominique MANIRY, Thomas WIEGARD, Wojciech SAMEK, Stephan KALTENSTADLER, Heiko SCHWARZ, Detlev MARPE, Mischa SIEKMANN, Martin WINKEN
  • Patent number: 11889066
    Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.
    Type: Grant
    Filed: June 13, 2022
    Date of Patent: January 30, 2024
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
    Inventors: Jonathan Pfaff, Philipp Helle, Dominique Maniry, Thomas Wiegard, Wojciech Samek, Stephan Kaltenstadler, Heiko Schwarz, Detlev Marpe, Mischa Siekmann, Martin Winken
  • Publication number: 20230254508
    Abstract: An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to: resample a second template of samples neighboring the current block, so as to conform with the first template so as to obtain a resampled template ; apply the resampled template of samples onto the neural network so as to obtain a preliminary intra-prediction signal; and resample the preliminary intra-prediction signal so as to conform with the current block so as to obtain the intra-prediction signal for the current block.
    Type: Application
    Filed: January 9, 2023
    Publication date: August 10, 2023
    Applicant: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
    Inventors: Jonathan Pfaff, Philipp Helle, Philipp Merkle, Björn Stallenberger, Mischa Siekmann, Martin Winken, Adam Wieckowski, Wojciech Samek, Stephan Kaltenstadler, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  • Patent number: 11601672
    Abstract: An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to: resample a second template of samples neighboring the current block, so as to conform with the first template so as to obtain a resampled template; apply the resampled template of samples onto the neural network so as to obtain a preliminary intra-prediction signal; and resample the preliminary intra-prediction signal so as to conform with the current block so as to obtain the intra-prediction signal for the current block.
    Type: Grant
    Filed: September 25, 2020
    Date of Patent: March 7, 2023
    Assignee: Fraunhofer-Gesellschaft zur Forderung der angewandten Forschung e.V.
    Inventors: Jonathan Pfaff, Philipp Helle, Philipp Merkle, Björn Stallenberger, Mischa Siekmann, Martin Winken, Adam Wieckowski, Wojciech Samek, Stephan Kaltenstadler, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  • Publication number: 20220321881
    Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.
    Type: Application
    Filed: June 13, 2022
    Publication date: October 6, 2022
    Inventors: Jonathan PFAFF, Philipp HELLE, Dominique MANIRY, Thomas WIEGARD, Wojciech SAMEK, Stephan KALTENSTADLER, Heiko SCHWARZ, Detlev MARPE, Mischa SIEKMANN, Martin WINKEN
  • Patent number: 11363259
    Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: June 14, 2022
    Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V., München
    Inventors: Jonathan Pfaff, Philipp Helle, Dominique Maniry, Thomas Wiegand, Wojciech Samek, Stephan Kaltenstadler, Heiko Schwarz, Detlev Marpe, Mischa Siekmann, Martin Winken
  • Publication number: 20210014531
    Abstract: An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to: resample a second template of samples neighboring the current block, so as to conform with the first template so as to obtain a resampled template; apply the resampled template of samples onto the neural network so as to obtain a preliminary intra-prediction signal; and resample the preliminary intra-prediction signal so as to conform with the current block so as to obtain the intra-prediction signal for the current block.
    Type: Application
    Filed: September 25, 2020
    Publication date: January 14, 2021
    Inventors: Jonathan PFAFF, Philipp HELLE, Philipp MERKLE, Björn STALLENBERGER, Mischa SIEKMANN, Martin WINKEN, Adam WIECKOWSKI, Wojciech SAMEK, Stephan KALTENSTADLER, Heiko SCHWARZ, Detlev MARPE, Thomas WIEGAND
  • Publication number: 20200244955
    Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.
    Type: Application
    Filed: April 10, 2020
    Publication date: July 30, 2020
    Inventors: Jonathan PFAFF, Philipp HELLE, Dominique MANIRY, Thomas WIEGAND, Wojciech SAMEK, Stephan KALTENSTADLER, Heiko SCHWARZ, Detlev MARPE, Mischa SIEKMANN, Martin WINKEN