公开(公告)号：US20240195966A1

公开(公告)日：2024-06-13

申请号：US18555396

申请日：2022-02-03

Applicant: Nokia Technologies Oy

Inventor： Sujeet Shyamsundar MATE ,  Yu YOU ,  Miska Matias HANNUKSELA ,  Saba AHSAN ,  Igor Danilo Diego CURCIO ,  Emre Baris AKSU

IPC: H04N19/119 ,  G06T3/16 ,  H04L12/18 ,  H04N19/162 ,  H04N19/167 ,  H04N19/17

CPC classification number: H04N19/119 ,  G06T3/16 ,  H04L12/1831 ,  H04N19/162 ,  H04N19/167 ,  H04N19/17

Abstract: Some embodiments relate to a method comprising receiving by a sender device omnidirectional video content for encoding; obtaining information of a viewport of a receiver device; obtaining information of a margin region outside the viewport; obtaining a margin update threshold parameter defining a threshold region within the margin region; based on the information of the viewport and the margin update threshold parameter determining whether to change the margin region; encoding the omnidirectional video content within the viewport with a first quality; encoding the omnidirectional video content within the margin region with a quality not higher than the first quality; and encoding the omnidirectional video content outside the viewport and the margin region with a third quality lower than the first quality and the quality of the margin region.

公开(公告)号：US20240171780A1

公开(公告)日：2024-05-23

申请号：US18551100

申请日：2022-03-09

Applicant: Nokia Technologies Oy

Inventor： Limin WANG ,  Seungwook HONG ,  Krit PANUSOPONE ,  Miska Matias HANNUKSELA

IPC: H04N19/70 ,  H04N19/17 ,  H04N19/186

CPC classification number: H04N19/70 ,  H04N19/17 ,  H04N19/186

Abstract: Example embodiments of the invention provide at least methods and apparatus to perform interpreting at an encoder of a communication network a region of at least one reconstructed picture: and based on the interpreting, generating compressed bits for generating the at least one reconstructed picture comprising at least one hash and using at least one specified variable, wherein based on the generating it can be determined whether or not the at least one hash of the at least one reconstructed picture is matched to at least one other hash. Further, to perform interpreting compressed bits for constructing at least one reconstructed picture, wherein at least one region of the at least one reconstructed picture comprises at least one hash and is using at least one specified variable, wherein the interpreting comprises generating at least one other hash: and comparing the at least one hash of the at least one reconstructed picture to the at least one other hash for determining whether or not at least one hash of the at least one reconstructed picture is matched to the at least one other hash.

公开(公告)号：US20240040131A1

公开(公告)日：2024-02-01

申请号：US18555536

申请日：2022-04-12

Applicant: Nokia Technologies Oy

Inventor： Miska Matias HANNUKSELA ,  Emre Baris AKSU ,  Kashyap KAMMACHI SREEDHAR

IPC: H04N19/172 ,  H04N19/136 ,  H04N19/132 ,  H04N19/70

CPC classification number: H04N19/172 ,  H04N19/136 ,  H04N19/132 ,  H04N19/70

Abstract: The embodiments relate to a method comprising indicating a video bitstream format wherein one or more image regions are allowed in a picture of a video bitstream (710); indicating at least a first substitute image region (720); indicating mapping information to locate the first substitute image region in the picture; wherein a first video bitstream comprising the first substitute image region at a location according to the mapping information conforms to the video bitstream format (730). The embodiments also concern a method at a receiver, and technical equipment for implementing the methods.

公开(公告)号：US20230412806A1

公开(公告)日：2023-12-21

申请号：US18334758

申请日：2023-06-14

Applicant: Nokia Technologies Oy

Inventor： Ruiying YANG ,  Francesco CRICRÌ ,  Maria Claudia SANTAMARIA GOMEZ ,  Honglei ZHANG ,  Miska Matias HANNUKSELA

IPC: H04N19/124 ,  H04N19/184 ,  H04N19/46

CPC classification number: H04N19/124 ,  H04N19/46 ,  H04N19/184

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example method includes determining one or more quantization parameters (quantizers) based at least on one or more of the following: a mean absolute value computed based on a set of parameters of a neural network comprising a parameter; a maximum absolute value computed based on a set of activations of the neural network comprising an activation; a number of parameters in the set of parameters of the neural network comprising the parameter; or a maximum absolute value computed based on an output value computed based on the parameter and the activation; and quantizing at least one of the parameter or the activation based at least on the one or more quantization parameters.

公开(公告)号：US20230154054A1

公开(公告)日：2023-05-18

申请号：US18053253

申请日：2022-11-07

Applicant: Nokia Technologies Oy

Inventor： Francesco CRICRÌ ,  Honglei ZHANG ,  Miska Matias HANNUKSELA ,  Hamed REZAZADEGAN TAVAKOLI ,  Nam Hai LE ,  Ramin GHAZNAVI YOUVALARI ,  Jukka AHONEN ,  Emre Baris AKSU

IPC: G06T9/00 ,  G06T3/40

CPC classification number: G06T9/002 ,  G06T3/4046

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example apparatus includes at least one processor; and at least one non-transitory memory comprising computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to iteratively perform following until a stopping criterion is met: provide a finetuning driving content (FDC) or a content derived from FDC to a decoder side neural network (DSNN); compute an output of the DSNN as a processed FDC; compute a loss based on the processed FDC and an approximated ground truth data (AGT) associated with the FDC; compute an update to the DSNN; and apply the computed update to the DSNN.

公开(公告)号：US20220272365A1

公开(公告)日：2022-08-25

申请号：US17739763

申请日：2022-05-09

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Miska Matias HANNUKSELA

IPC: H04N19/33 ,  H04N19/46 ,  H04N19/105 ,  H04N19/136 ,  H04N19/70 ,  H04N19/172

Abstract: There is provided methods, apparatuses and computer program products for video coding and decoding. A first part of a first coded video representation is decoded, and information on decoding a second coded video representation is received and parsed. The coded second representation differs from the first coded video representation in chroma format, sample bit depth, color gamut and/or spatial resolution, and the information indicates if the second coded video representation may be decoded using processed decoded pictures of the first coded video representation as reference pictures. If the information indicates that the second coded video representation may be decoded using processed decoded pictures of the first coded video representation as a prediction reference, decoded picture(s) of the first part is/are processed into processed decoded picture(s) by resampling and/or sample value scaling; and decoding a second part of a second video representation using said processed decoded picture(s) as reference pictures.

公开(公告)号：US20210397965A1

公开(公告)日：2021-12-23

申请号：US17354398

申请日：2021-06-22

Applicant: Nokia Technologies Oy

Inventor： Honglei ZHANG ,  Francesco CRICRI ,  Hamed REZAZADEGAN TAVAKOLI ,  Joachim WABNIG ,  Iraj SANIEE ,  Miska Matias HANNUKSELA ,  Emre AKSU

IPC: G06N3/08 ,  G06N3/04

Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: estimate an importance of parameters of a neural network based on a graph diffusion process over at least one layer of the neural network; determine the parameters of the neural network that are suitable for pruning or sparsification; remove neurons of the neural network to prune or sparsify the neural network; and provide at least one syntax element for signaling the pruned or sparsified neural network over a communication channel, wherein the at least one syntax element comprises at least one neural network representation syntax element.

公开(公告)号：US20210218999A1

公开(公告)日：2021-07-15

申请号：US17140580

申请日：2021-01-04

Applicant: Nokia Technologies Oy

Inventor： Sebastian SCHWARZ ,  Lukasz KONDRAD ,  Emre AKSU ,  Lauri ILOLA ,  Vinod Kumar MALAMAL VADAKITAL ,  Miska Matias HANNUKSELA

IPC: H04N19/70 ,  H04N19/597

Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: provide signal information to identify an atlas identifier on a sample of a volumetric media track, or on the volumetric media track in a multi-track container; wherein the signal information allows a file parser to link volumetric media tracks with different atlas identifiers that originate from a volumetric media elementary stream; and wherein the file parser is able to reconstruct the volumetric media elementary stream based on the signal information and data encapsulated in the multi-track container.

公开(公告)号：US20200304949A1

公开(公告)日：2020-09-24

申请号：US16823749

申请日：2020-03-19

Applicant: Nokia Technologies Oy

Inventor： Sujeet Shyamsundar MATE ,  Emre Baris AKSU ,  Miska Matias HANNUKSELA ,  Igor Danilo Diego CURCIO ,  Kashyap KAMMACHI-SREEDHAR ,  Ville-Veikko MATTILA

IPC: H04W4/02 ,  G06T19/00 ,  G06F3/01

Abstract: A method, apparatus and computer program product creates a viewpoint position structure for media content. The viewpoint position structure specifies a position of a viewpoint defined in a reference coordinate system and an offset of the reference coordinate system with respect to a geographical reference. The method, apparatus and computer program product cause storage of the viewpoint position structure. An indication may be created as to whether the media content is augmented reality media content. The augmented reality media content may comprise a background that is at least partially transparent. The offset may be determined, within the reference coordinate system, relative to a geomagnetic reference direction, based upon one or more of a viewpoint yaw angle, a viewpoint pitch angle, or a viewpoint roll angle.

公开(公告)号：US20200092572A1

公开(公告)日：2020-03-19

申请号：US16689582

申请日：2019-11-20

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Miska Matias HANNUKSELA ,  Kemal UGUR

IPC: H04N19/463 ,  H04N19/30 ,  H04N19/61 ,  H04N19/70

Abstract: A method comprising encoding a bitstream comprising a base layer, a first enhancement layer and a second enhancement layer; encoding an indication of both the base layer and the first enhancement layer used for prediction for the second enhancement layer in the bitstream; encoding, in the bitstream, an indication of a first set of prediction types that is applicable from the base layer to the second enhancement layer, wherein the first set of prediction types is a subset of all prediction types available for prediction between layers, and encoding, in the bitstream, an indication of a second set of prediction types that is applicable from the base layer or the first enhancement layer to the second enhancement layer, wherein the second set of prediction types is a subset of all prediction types available for prediction between layers.