Nokia Technologies Oy

Nokia Corporation

Core Wireless Licensing S.a.r.l.

Nokia Mobile Phones Limited

Microsoft Technology Licensing, LLC

Nokia Oy

Roac Nd Investments L.l.c.

Sisvel International S.a.

Miska Matias Hannuksela

Emre Baris Aksu

Ye-Kui Wang

Jani Lainema

Kemal Ugur

Sujeet Shyamsundar Mate

Francesco Cricri

Igor D Curcio

Kashyap Kammachi Sreedhar

Hamed Rezazadegan Tavakoli

Ying Hai Chen

Vinod Kumar Malamal Vadakital

Igor Danilo Diego Curcio

Sebastian Schwarz

Dmytro Rusanovskyy

Ari Hourunranta

Alireza Aminlou

Francesco Cricrì

Lukasz Kondrad

Imed Bouazizi

Srikanth Manchenahally Gopalakrishna

Honglei Zhang

Matti Salmi

Roberto Castagno

Stephan Wenger

Dogu Cetin

Mika Rantanen

Saba Ahsan

Lauri Ilola

Mehmet Oguz Bici

Lauri Aleksi Ilola

Caglar Aytekin

Kashyap Kammachi-Sreedhar

Chenghao Liu

Nam Le

Alireza Zare

Ying Chen

Antti Johannes Eronen

Harri Juhani Pekonen

Yu You

Pekka Talmola

Mikko Johannes Honkala

Marja Salmimaa

Timo Juhani Ahonen

Daniel Vaquero

Kerem Caglar

Ramin Ghaznavi Youvalari

Jonne Juhani Mäkinen

Juha-Pekka Hippeläinen

Xianglin Wang

Limin Wang

Krit Panusopone

Seungwook Hong

Jussi Leppanen

Vidya Raghavan Setlur

Pasi Sakari Ojala

Jussi Vesma

Toni Paila

Antti Hallapuro

Iraj Saniee

Houqiang Li

David Leon

Ville-Veikko Mattila

Payman Aflaki Beni

Suresh Chitturi

Ramakrishna Vedantham

Joachim Wabnig

Dominique Müller

Michael Ingrassia

Tolga Capin

Viktor Varsa

Xingyang Ni

Atanas Gotchev

Tuomas Virtanen

Peter O Fasogbon

Yi Guo

Mihail Georgiev

Ali Karaoglu

Nannan Zou

Roope Olavi Jarvinen

Mehdi Rezaei

Christoph Bachhuber

Yat Hong Lam

Toni Heittola

Annamaria Mesaros

Ye Kui Wang

Jani Toiminen

Daidi Zhong

Ru Shang Wang

Dong Tian

Payman Aflaki-Beni

Justin Ridge

Olli Kilpelainen

Jani Kattelus

There is disclosed a method, an apparatus and a computer program product for video encoding and decoding. In accordance with an embodiment the method comprises obtaining coded data of a sub-picture, the sub-picture belonging to a picture, and the sub-picture belonging to a sub-picture sequence and determining whether to use the sub-picture as a source for a manipulated reference sub-picture. If the determining reveals that the sub-picture is to be used as the source for the manipulated reference sub-picture, the manipulated reference sub-picture is generated from the sub-picture to be used as a reference for a subsequent sub-picture of the sub-picture sequence.

Apparatus, a method and a computer program for video coding and decoding

The embodiments relate to a method comprising receiving an encoded video comprising a GDR picture and recovering pictures following the GDR picture in decoding order; decoding information that a slice-based GDR is in use, wherein each of the GDR picture and the recovering pictures comprises a first set of slices comprising a clean area and a second set of slices comprising rest of the picture; relabeling the GDR picture as an intra-coded random access point picture in a modified bitstream; including only the first set of slices of the GDR picture and the recovering pictures into the modified bitstream; decoding information on a picture width and height of each of the GDR picture and the recovering pictures; modifying the picture width and height to exclude the second set of slices; and including the modified information on the picture width and height to the modified bitstream.

Method, an apparatus and a computer program product for implementing gradual decoding refresh

The embodiments relate to a method for encoding two or more tensors. The method comprises processing the two or more tensors having respective dimensions so that the dimensions of said two or more sensors have the same number (); identifying which axis of each individual tensor is swappable to result in concatenable tensors around an axis of concatenation (); reshaping the tensors so that the dimensions are modified based on the swapped axis (); concatenating the tensors around the axis of concatenation to result in concatenated tensor (); compressing the concatenated tensor (); generating syntax structures for carrying concatenation and axis swapping information (); and generating a bitstream by combining the syntax structures and the compressed concatenated tensor (). The embodiments also relate to a method for decoding, and to apparatuses for implementing the methods.

Method, an apparatus and a computer program product for neural network compression

A method comprising obtaining a 360-degree video content from a video source; projecting the 360-degree video content onto a 2D image plane; dividing the projected 360-degree video content into a plurality of regions, wherein the regions are partly overlapping and each region covers a region of the 360-degree video content suitable for a viewport presentation; receiving a request for a viewport orientation of the 360-degree video content from a client; and providing the client with an viewport presentation of the region corresponding to the requested viewport orientation.

Method, an apparatus and a computer program product for video conferencing

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.

A method, apparatus, and computer program product provide for management of luma mapping with chroma scaling (LMCS) processes for Gradual Decoding Refresh (GDR) pictures. In the context of a method, the method accesses a picture to be decoded and determines whether the picture is within a GDR period. The method can also prevent a LMCS decoding process from being applied to the picture within the GDR period. Another method can determine whether a virtual boundary is within a current coding tree unit of a picture with a GDR period and if so, prevent a chroma residual scaling decoding process associated with LMCS from being applied to one or more coding units within a clean area. Another method can pad a neighboring pixel area from one or more reconstructed pixels in a clean area for a chroma residual scaling decoding process associated with LMCS.

Luma mapping with chroma scaling for gradual decoding refresh

Four or more bitstream versions of a same content are encoded and divided into segments of independently coded tile sets representing multiple spatial regions. First and second bitstreams include independently coded tile sets encoded at a first quality. Third and fourth bitstreams include independently coded tile sets encoded at a second quality. First and third bitstreams have first random access picture interval. Second and fourth bitstreams have second random access picture interval. Independently coded tile sets are grouped into multiple groups of collocated sub-picture tracks, only one of said tile sets per group is intended to be received and/or decoded per any segment. Instruction(s) are generated for merging tile sets of different spatial locations into coded picture(s), causing a tile set originating from a random access picture to be decoded as a tile set originating from a non-random-access picture when merged with a tile set originating from a non-random-access picture.

Various embodiments provide an apparatus, a method, and a computer program product. 1. An apparatus incudes at least one processor; and at least one non-transitory memory includes 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 an overfitting operation, at an encoder side, to obtain an overfitted probability model, wherein overfitting comprises one or more training operations applied to a probability model, wherein one or more parameters of the probability model are trained; use the overfitted probability model to provide probability estimates to a lossless codec or a substantially lossless codec for encoding data or a portion of the data; and signal information to a decoder on whether to perform the overfitting operation at the decoder side.

Apparatus method and computer program product for probability model overfitting

An apparatus includes circuitry configured to: receive a sequence of pictures; encode a picture among the sequence of pictures as one or more slices and one or more tiles, wherein a slice comprises an integer number of tiles or is included in a tile; encode, into a slice header of a slice of the one or more slices, a subpicture identifier indicative of a subpicture that comprises the slice; wherein the subpicture identifier is indicative of a subpicture position for the subpicture comprising the slice, the subpicture identifier being among one or more subpicture identifiers indicative of one or more subpicture positions for one or more subpictures comprising one or more slices; and wherein the subpicture is an independently decodable spatiotemporal unit characterized in that a sequence of collocated subpictures is decodable independently of other subpictures.

Method and apparatus for tile-relative addressing in video coding

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.

Graph diffusion for structured pruning of neural networks

A method is provided for defining a metadata box of a neural network representation (NNR) item data, wherein the NNR item data comprises an NNR bitstream; and defining an association between the NNR item data and an NNR configuration by using a configuration item property, wherein the NNR configuration item property comprises information about stored NNR item data. Corresponding apparatuses and computer program products are also provided.

Carriage and signaling of neural network representations

A reference picture marking process and a reference picture list management process is handled in a unified reference picture marking and reference picture list management process. A new idle reference picture list may be used for handling reference pictures that are not used for reference in the current picture. Differential coding of picture order count may be used to increase coding efficiency. The reference picture management syntax structure may be sent in the picture parameter set for improved coding efficiency e.g. in regular GOP (group of pictures) arrangements.

Reference picture handling

A method, apparatus and computer program product are provided to signaling multiple media data types in a container file format, for example, ISOBMFF, in an efficient manner. In the context of a signaling method, media type definitions overloaded in an instance a plurality of media type definitions is present in compatible media type list, wherein a media type definition is associated with a media type. The method then indicates, using the compatible media type list, presence of a plurality of media types in a metadata or multimedia box. Corresponding apparatuses and computer program products are also provided.

Method and apparatus for signaling multiple media data types

There are disclosed various methods, apparatuses and computer program products for video encoding and decoding. In some embodiments the method for video encoding comprises obtaining compressed volumetric video data representing a three-dimensional scene or object (); capsulating the compressed volumetric video data into a data structure (); obtaining data of a two-dimensional projection of at least a part of the three-dimensional scene as seen from a certain viewport (); and including the data of the two-dimensional projection into the data structure ().

Apparatus, a method and a computer program for omnidirectional video

Example embodiments provide a system for training a data coding pipeline including a feature extractor neural network, an encoder neural network, and a decoder neural network configured to reconstruct input data based on encoded features. A plurality of losses corresponding to different tasks may be determined for the coding pipeline. Tasks may be performed based on an output of the coding pipeline. A weight update may be determined for at least a subset of the coding pipeline based on the plurality of losses. The weight update may be configured to reduce a number of iterations for fine-tuning the coding pipeline for one of the tasks. This enables faster adaptation of the coding pipeline for one of the tasks after deployment of the coding pipeline. Apparatuses, methods, and computer programs are disclosed. Apparatuses, methods, and computer programs are disclosed.

Training a data coding system comprising a feature extractor neural network

Growing community of inventors

Tampere, Finland

Miska Matias Hannuksela