公开(公告)号：US12244814B2

公开(公告)日：2025-03-04

申请号：US17975842

申请日：2022-10-28

Applicant: ATEME

Inventor： Anthony Nasrallah ,  Thomas Guionnet ,  Mohsen Abdoli

IPC: H04N19/136 ,  H04N19/154 ,  H04N19/189

Abstract: A method of processing a video sequence is proposed, which comprises, for a video encoding tool of a set of video encoding tools configured for encoding the video sequence comprised in a video encoder, determining an efficiency value based on an encoding performance value and an encoding computational complexity value of the video encoding tool for encoding the video sequence, and determining, based on the efficiency value of the video encoding tool, whether to configure the video encoder to use the video encoding tool for the encoding of the video sequence.

公开(公告)号：US20230199204A1

公开(公告)日：2023-06-22

申请号：US18086964

申请日：2022-12-22

Applicant: ATEME

Inventor： Abdelmajid Moussaoui ,  Sassan Pejhan ,  Thomas Guionnet ,  Chrystelle Le Gall ,  David Bouchard

IPC: H04N19/42 ,  H04N19/105 ,  H04N19/136 ,  H04N19/50 ,  H04N19/156 ,  G06N3/09

CPC classification number: H04N19/42 ,  H04N19/105 ,  H04N19/136 ,  H04N19/50 ,  H04N19/156 ,  G06N3/09

Abstract: A method for managing encoding of multimedia content stored in a file is proposed, which comprises: determining, using a supervised learning algorithm, a prediction of processing resources required for encoding the multimedia content, based on one or more multimedia content characteristics of the multimedia content and on one or more multimedia content encoding parameters for encoding the multimedia content; and determining a processing configuration for encoding the multimedia content based on the prediction of processing resources.

公开(公告)号：US11240521B2

公开(公告)日：2022-02-01

申请号：US17307364

申请日：2021-05-04

Applicant: ATEME

Inventor： Thomas Guionnet ,  Sébastien Herbreteau

IPC: G06T5/00 ,  H04N19/46 ,  H04N5/262 ,  H04N19/36

Abstract: A method of method of processing an image includes: determining estimates of parameters of an auto-regressive, parametric model of noise, according to which a current noise pixel is computed combining linear combination of previous noise pixels in a causal neighborhood of the current noise pixel weighted by respective model linear combination parameters with a generated noise sample corresponding to an additive Gaussian noise of model variance parameter; performing a convergence check loop, each iteration including: generating a noise template of noise pixels based on the estimated model parameters, the noise template having predetermined pixel size smaller than the image pixel size; estimating a noise template variance; if the estimated variance is below a first predetermined threshold or above a second predetermined threshold, proportionally decreasing the model linear combination parameters with a predetermined correcting factor, and performing another convergence check loop; otherwise exiting the convergence check loop.

公开(公告)号：US20220141460A1

公开(公告)日：2022-05-05

申请号：US17517878

申请日：2021-11-03

Applicant: ATEME

Inventor： Anthony Nasrallah ,  Thomas Guionnet ,  Mohsen Abdoli ,  Marco Cagnazzo ,  Attilio Fiandrotti

IPC: H04N19/117 ,  H04N19/105 ,  H04N19/139 ,  H04N19/176 ,  G06T9/00 ,  G06N3/08

Abstract: A method of processing a first image in a first plurality of images, wherein the first image is divided into a plurality of pixel blocks, is proposed, which comprises, for a current block of the first image: selecting, in a set of a plurality of predefined interpolation filters, an interpolation filter based on a prediction of an interpolation filter determined by a supervised learning algorithm to which data related to the current block is input; and using the selected interpolation filter for calculating fractional pixel values in a second image of the plurality of images for a temporal prediction of pixels of the current block based on a reference block correlated to the current block in the second image, wherein the second image is distinct from the first image and was previously encoded according to an image encoding sequence for encoding the images of the plurality of images.

公开(公告)号：US20220038748A1

公开(公告)日：2022-02-03

申请号：US17390509

申请日：2021-07-30

Applicant: ATEME

Inventor： Thomas Guionnet ,  Sébastien Herbreteau

IPC: H04N19/85 ,  G06T5/00

Abstract: A method of processing an image is proposed, which includes: determining, based on the image, one or more noise templates, wherein each of the one or more noise templates includes noise pixels representing noise contained in the image; calculating one or more first autocovariance values, based on the noise pixels of at least one of the one or more noise templates; based on the one or more first autocovariance values, selecting an entry of a noise model database among database entries which respectively include values of noise model parameters corresponding to a noise model.

公开(公告)号：US20190281337A1

公开(公告)日：2019-09-12

申请号：US16280459

申请日：2019-02-20

Applicant: ATEME

Inventor： Thomas Guionnet

IPC: H04N21/2662 ,  H04N21/2343 ,  H04N21/238

Abstract: A method, implemented by computer means, for digitally encoding multimedia content into one or more video streams for on-demand distribution to at least one receiving terminal, the method comprising the following steps: from a given set of profiles, each profile being characterized by a value of at least one encoding parameter, forming one or more ordered groups of profiles, it being possible for a same profile to be present in multiple groups, such that in each group, each profile and its immediate successor satisfy a first predetermined condition, and selecting from the formed groups at least one group of profiles satisfying a second predetermined condition.

公开(公告)号：US20230283825A1

公开(公告)日：2023-09-07

申请号：US18098443

申请日：2023-01-18

Applicant: ATEME

Inventor： Abdelmajid Moussaoui ,  Thomas Guionnet ,  Sassan Pejhan

IPC: H04N21/266 ,  H04N21/24 ,  H04N21/2385

CPC classification number: H04N21/266 ,  H04N21/2405 ,  H04N21/2402 ,  H04N21/2385

Abstract: A method for managing computational resources allocated for encoding of one or more multimedia content streams for distribution in dynamic mode to viewing devices through a distribution network is proposed, which comprises, by a processing node of the distribution network: obtain, for a multimedia content stream corresponding to a channel distributed to the viewing devices, a value of a computational resource allocation criterion, wherein the computational resource allocation criterion comprises an audience measurement for the corresponding channel and a video content complexity of the multimedia content stream; and determine, based on the computational resource allocation criterion, an allocation of computational resources of a computing platform configured for encoding the multimedia content stream.

公开(公告)号：US20220345715A1

公开(公告)日：2022-10-27

申请号：US17642578

申请日：2020-09-09

Applicant: ATEME

Inventor： Thomas Guionnet ,  Josselin Cozanet

IPC: H04N19/137 ,  H04N19/105 ,  H04N19/52 ,  H04N19/176 ,  G06N3/08

Abstract: A method for encoding a first image within a first set of images, in which the first image is cut into blocks, each block being encoded according to one among a plurality of coding modes, is proposed, which comprises, for a current block of the first image, the determination, on the basis of at least one second image distinct from the first image and previously encoded according to an encoding sequence of the images of the first set of images, of a prediction of a feature of the current block in one or more third images from the first set of images distinct from the first image and not yet encoded according to the encoding sequence, and the use of the prediction to encode the current block while minimizing a flow-distortion criterion.

公开(公告)号：US11483590B2

公开(公告)日：2022-10-25

申请号：US17307339

申请日：2021-05-04

Applicant: ATEME

Inventor： Thomas Guionnet ,  Sébastien Herbreteau

IPC: H04N19/86 ,  H04N19/182 ,  G06T5/00 ,  G06T5/50

Abstract: A method of method of processing an image includes: determining estimates of parameters of an auto-regressive, AR, parametric model of noise contained in the image, according to which a current noise pixel is computed as a combination of a linear combination of P previous noise pixels in a causal neighborhood of the current noise pixel weighted by respective AR model linear combination parameters (φ1, . . . , φP) with a generated noise sample corresponding to an additive Gaussian noise of AR model variance parameter (σ), generating a noise template of noise pixels based on the estimated AR model parameters, wherein the noise template is of a predetermined pixel size smaller than the pixel size of the image, determining an estimate (σP) of a variance of the noise template, and based on a comparison of the estimated variance (σP) with a predetermined threshold (Tσ), correcting the AR model variance parameter (σ).

公开(公告)号：US11138703B2

公开(公告)日：2021-10-05

申请号：US16958935

申请日：2018-12-21

Applicant: ATEME

Inventor： Thomas Guionnet

IPC: G06T5/00 ,  G06T5/50

Abstract: Disclosed is a method for processing a video stream including a set of images liable to contain a transition effect, the method including the following steps: detecting a fade-type transition effect within the set of images of the video stream and, where appropriate, calculating minimum and maximum brightnesses LMIN and LMAX for each image of the set of images containing the fade; estimating minimum and maximum brightnesses EMIN and EMAX for all of the images not containing the detected transition effect; determining minimum and maximum brightnesses SMIN and SMAX for a standard dynamic range; calculating minimum and maximum brightnesses TMIN and TMAX depending on the minimum and maximum brightnesses LMIN, LMAX, EMIN, EMAX, SMIN and SMAX calculated and determined beforehand; transmitting the calculated minimum and maximum brightnesses TMIN and TMAX with a view to dynamic range compression.