Abstract: A method, apparatus and computer program product are provided to signal and store compressed point clouds in video encoding. The method, apparatus and computer program product may be utilized in conjunction with a variety of video formats. Relative to encoding of compressed point clouds, the method, apparatus and computer program product access a point cloud compression coded bitstream and cause storage of the point cloud compression coded bitstream. The point cloud compression coded bitstream comprises a texture information bitstream, a geometry information bitstream, and an auxiliary metadata bitstream. Relative to the decoding of compressed point clouds, the method, apparatus and computer program product receive a point cloud compression coded bitstream and decode the point cloud compression coded bitstream.

Abstract: Data may be encoded to minimize distortion after decoding, but the quality required for presentation of the decoded data to a machine and the quality required for presentation to a human may be different. To accommodate different quality requirements, video data may be encoded to produce a first set of encoded data and a second set of encoded data, where the first set may be decoded for use by one of a machine consumer or a human consumer, and a combination of the first set and the second set may be decoded for use by the other of a machine consumer or a human consumer. The first and second set may be produced with a neural encoder and a neural decoder, and/or may be produced with the use of prediction and transform neural network modules. A human-targeted structure and a machine-targeted structure may produce the sets of encoded data.

Abstract: 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.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. The 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: define or utilize file format syntax elements to indicate samples comprising at least one of: one or more description documents, wherein the one or more description documents comprise 3 dimensional information; or one or more updates to at least one description document of the one or more description documents; and define or utilize the file format syntax elements to indicate a relationship between samples containing the one or more description document and update information to the samples.

Abstract: A method comprising: authoring a plurality of sets of media tracks comprising at least a first set of media tracks and a second set of media tracks into a media file format, wherein a subset of tracks of the first set comprises alternate data for each other and a subset of tracks of the second set comprises alternate data for each other; and including, in or along a bitstream comprising a media file including or inferring said media tracks, an indication that said subset of tracks of the first set are alternatives to each other and said subset of tracks of the second set are alternatives to each other upon playback of the media tracks.

Abstract: An apparatus includes circuitry configured to: receive a plurality of compressed residual local weight updates from a plurality of respective institutes with a plurality of a respective first parameter, the first parameter used to determine a plurality of respective predicted local weight updates; determine a plurality of local weight updates or a plurality of adjusted local weight updates based on the plurality of compressed residual local weight updates and the plurality of respective predicted local weight updates; aggregate the plurality of determined local weight updates or the plurality of adjusted local weight updates to generate an intended global weight update, and update a model on a server based at least on the intended global weight update, the model used to perform a task; and transfer a compressed residual global weight update to the institutes with a second parameter, the second parameter used to determine a predicted global weight update.

Abstract: A method comprising: writing, in a container file, a first video-based point cloud compression (V-PCC) bitstream and a second V-PCC bitstream, wherein said first and second V-PCC bitstreams are associated with a common group based on at least one logical context; writing, in the container file, an indication about the common group between the first V-PCC bitstream and the second V-PCC bitstream; generating a media presentation description (MPD) file with a first representation belonging to a first adaptation set associated with the first V-PCC bitstream and a second representation belonging to a second adaptation set associated with the second V-PCC bitstream; and writing, in the MPD file, at least one information element describing grouping information of the first representation belonging to the first adaptation set and the second representation belonging to the second adaptation set, wherein said information element is provided with at least one attribute indicating that said first and second V-PCC bitstre

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.

Abstract: An example method is provided to include receiving a media bitstream comprising one or more media units and a first enhancement information message, wherein the first enhancement information message comprises at least two independently parsable structures, a first independently parsable structure comprising information about at least one purpose of one or more neural networks (NNs) to be applied to the one or more media units, and a second independently parsable structure comprising or identifying one or more neural networks; decoding the one or more media units; and using the one or more neural networks to enhance or filter one or more frames of the decoded the one or more media units, based on the at least one purpose. An example method includes. Corresponding apparatuses and computer program products are also provided.

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: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit having metadata or compressed neural network data of a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information unit.

Abstract: A method includes generating a bitstream defining a presentation, the presentation comprising an omnidirectional visual media content and a first visual media component and a second visual media component; indicating in the bitstream a first presentation timeline and a second presentation timeline; and indicating in the bitstream a switching mode with respect to the first presentation timeline associated with the first visual media component, or with respect to the second presentation timeline associated with the second visual media component, the switching mode being indicated dependent on a viewpoint of a user; wherein the switching mode provides an indication of switching to the first visual media component or to the second visual media component, the first visual media component corresponding to content captured from a first omnidirectional camera in a first location, and the second visual media component corresponding to content captured from a second omnidirectional camera in a second location.

Abstract: A method, apparatus and computer program product encode, into a media description, a first information item indicative of a first locator for segment metadata for a set of representations. The method, apparatus and computer program product encode, into the media description, one or more representation-specific information items indicative of representation-specific locator for segment media data for one or more representations of the set of representations. The method, apparatus and computer program product cause storage of the media description with the set of representations.

Abstract: The invention relates to a solution wherein a bitstream defining a presentation is generated, the presentation comprising an omnidirectional visual media content and a first visual media component and a second visual media component; indicating in the bitstream a first presentation timeline associated with the first visual media component; indicating in the bitstream a second presentation timeline associated with the second visual media component; indicating in the bitstream a switching mode to a second presentation timeline associated with the second visual media component; and indicating in the bitstream, that the switching mode is with respect to the first presentation timeline or to the second presentation timeline.

Abstract: A system, obtaining a first training dataset, comprising a plurality of first image and pose data pairs; obtaining a first generated dataset, comprising a plurality of first image and estimated pose data pairs, wherein estimated pose data of the first image and estimated pose data pairs are generated by a first neural network trained using the first training dataset; obtaining a second generated dataset, comprising a plurality of second image and estimated pose data pairs, wherein estimated pose data of the second image and estimated pose data pairs are generated by a second neural network trained using the first training dataset; generating the first and second generated datasets a generated training dataset, comprising image and estimated pose data pairs selected from said first generated dataset; and training a third neural network based on a combination of some or all of the first training dataset and the generated training dataset.

Abstract: A node for a federated machine learning system that comprises the node and one or more other nodes configured for the same machine learning task, the node comprising: a federated student machine learning network configured to update a machine learning model in dependence upon updated machine learning models of the one or more node; a teacher machine learning network; means for receiving unlabeled data; means for teaching, using supervised learning, at least the federated first machine learning network using the teacher machine learning network, wherein the teacher machine learning network is configured to receive the data and produce pseudo labels for supervised learning using the data and wherein the federated student machine learning network is configured to perform supervised learning in dependence upon the same received data and the pseudo-labels.

Abstract: A method, apparatus and computer program product access a video-based point cloud compression coded bitstream. The point cloud compression coded bitstream corresponds to a non-timed video-based point cloud compression representation that comprises one or more video point cloud compression units. The method, apparatus and computer program product encapsulate the one or more video point cloud compression units as one or more video point cloud compression unit items. The method, apparatus and computer program product also cause storage of the one or more video point cloud compression unit items in a file.

Abstract: A method comprising: writing, in a container file, a first video-based point cloud compression (V-PCC) bitstream and a second V-PCC bitstream, wherein said first and second V-PCC bitstreams are associated with a common group based on at least one logical context; writing, in the container file, an indication about the common group between the first V-PCC bitstream and the second V-PCC bitstream; generating a media presentation description (MPD) file with a first representation belonging to a first adaptation set associated with the first V-PCC bitstream and a second representation belonging to a second adaptation set associated with the second V-PCC bitstream; and writing, in the MPD file, at least one information element describing grouping information of the first representation belonging to the first adaptation set and the second representation belonging to the second adaptation set, wherein said information element is provided with at least one attribute indicating that said first and second V-PCC bitstre

Abstract: The invention relates to a method, an apparatus and a computer program product for analyzing media content. The method comprises receiving media content; performing feature extraction of the media content at a plurality of convolution layers to produce a plurality of layer-specific feature maps; transmitting from the plurality of convolution layers a corresponding layer-specific feature map to a corresponding de-convolution layer of a plurality of de-convolution layers via a recurrent connection between the plurality of convolution layers and the plurality of de-convolution layers; and generating a reconstructed media content based on the plurality of feature maps.

Abstract: Data may be encoded to minimize distortion after decoding, but the quality required for presentation of the decoded data to a machine and the quality required for presentation to a human may be different. To accommodate different quality requirements, video data may be encoded to produce a first set of encoded data and a second set of encoded data, where the first set may be decoded for use by one of a machine consumer or a human consumer, and a combination of the first set and the second set may be decoded for use by the other of a machine consumer or a human consumer. The first and second set may be produced with a neural encoder and a neural decoder, and/or may be produced with the use of prediction and transform neural network modules. A human-targeted structure and a machine-targeted structure may produce the sets of encoded data.

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: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit having metadata or compressed neural network data of a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information unit.