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: receive a scene description comprising data associated with a scene; place the data associated with the scene into data buffers and create command buffers; adapt the data placed within the data buffers and synchronize the data within the data buffers with information provided from local media or network media; signal information about the adaptation to update the command buffers that command a renderer; and render the scene using the data within the data buffers and the command buffers.

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: decode encoded data to generate decoded data, the encoded data having a bitrate lower than that of original data, and extract features from the decoded data; decode encoded residual features to generate decoded residual features; and generate enhanced decoded features as a result of combining the decoded residual features with the features extracted from the decoded data.

Abstract: An apparatus includes circuitry configured to: partition an input tensor into one or more block tensors; partition at least one of the block tensors into one or more continuation bands, the one or more continuation bands being associated with a caching counter having a value; store the one or more continuation bands in a cache managed using a cache manager; retrieve, prior to a convolution or pooling operation on a current block tensor, the one or more continuation bands of a previous block tensor from the cache that are adjacent to a current block tensor; concatenate the retrieved continuation bands with the current block tensor; apply the convolution or pooling operation on the current block tensor after the concatenation; decrease the respective caching counter value of the retrieved continuation bands; and clear the continuation bands from the cache when its respective caching counter reaches a value of zero.

Abstract: Video data is obtained or received. At least a current frame or previous frame(s) of the obtained or received video data are provided to an input of a neural network. A predicted output is generated at an output of the neural network. The predicted output includes at least one of predicted future frame(s) of the video data and predicted properties of future frame(s) of the video data. Processing decision(s) are determined based, at least in part, on the predicted output. The current frame of the video data is processed at least partially according to the processing decision(s).

Abstract: A method comprising: encoding video media content into at least a first representation and a second representation, wherein the first representation comprises a switchable inter-coded picture, wherein the switchable picture has a first characteristic that no pictures preceding the switchable picture in decoding order are used as reference pictures for any non-switchable pictures following the switchable picture in decoding order; and the second representation comprises one or more decoder reset pictures aligned with the switchable pictures of the first representation, wherein the frame rate of the second representation is smaller than or equal to the frame rate of the first representation and the resolutions of the first and the second representation are equal.

Abstract: A method, apparatus and computer program product create a media presentation description with a first representation set and a second representation set. The first representation set belongs to a first adaptation set and the second representation set belongs to a second adaptation set and the first representation set is associated with the first media entity and the second representation set is associated with the second media entity. The method, apparatus and computer program product encode, in the media presentation description, an adaptation and representation grouping descriptor. The adaptation and representation grouping descriptor groups the first representation set with the second representation set based on the grouping type.

Abstract: A method includes maintaining a set of parameters or weights derived through online learning for a neural net; transmitting an update of the parameters or weights to a decoder; deriving a first prediction block based on an output of the neural net using the parameters or weights; deriving a first encoded prediction error block through encoding a difference of the first prediction block and a first input block; encoding the first encoded prediction error block into a bitstream; deriving a reconstructed prediction error block based on the first encoded prediction error block; deriving a second prediction block based on an output of the neural net using the parameters or weights and the reconstructed prediction error block; deriving a second encoded prediction error block through encoding a difference of the second prediction block and a second input block; and encoding the second encoded prediction error block into a bitstream.

Abstract: An apparatus includes at least one processor; and at least one 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: indicate an extraction reference map entry used to assign a group identifier to at least one extraction reference, the extraction reference map entry indicating a subpicture layout; wherein the at least one extraction reference causes extraction of a network abstraction layer unit data by reference from another track; wherein the at least one extraction reference comprises an index of a track reference having a subpicture type within a subpicture order sample group description entry; and indicate, using the at least one extraction reference, subpictures or slices of a coded picture in decoding order.

Abstract: Feature information is received from a client device and describes extended reality scene(s) in an extended reality (ER) environment at the client device. An ER description is formed in an ER description format corresponding to the feature information and is stored. Some of the stored ER description format is provided in a representational format upon request of the client device or other client devices viewing the one or more ER scenes and assisting the positioning of corresponding client devices in the ER environment. A client device captures environmental visual data and generates feature information, describing ER scene(s) in an extended reality environment at the client device, from the environmental visual data, and sends the generated feature information toward a server. A client device can localize itself in a 3D environment of an ER description, and generate ER anchors and objects, link them, and send them to a server.

Abstract: A method, apparatus and computer program product to signal and store various segment properties in omnidirectional media, including sizes, priority ranks, and the like. The method, apparatus and computer program product access one or more media segments (30). The one or more media segments includes media data configured for streaming playback. The method, apparatus and computer program product access size information (32) or priority rank information of one or more tiles for each of the one or more media segments. The method, apparatus and computer program product encode the size information (34) or priority rank information for each of the one or more media segments in a media file within one or more metadata tracks associated with the one or more media segments or one or more sub-segments associated with the one or more media segments.

Abstract: A user equipment, media control unit, media resource function, or another device or function capable of receiving, manipulating, and transmitting data may be configured to: receive an omnidirectional video; determine a viewport of a user equipment; determining a delivery mode; determine a region of the omnidirectional video based, at least partially, on the determined viewport and the determined delivery mode; encode the determined region; packetizing the encoded region; and transmit the packetized region to the user equipment based, at least partially, on the determined delivery mode.

Abstract: A method comprising: deriving a first prediction block (608) at least partly based on an output of a neural net (602) using a first set of parameters; deriving a first encoded prediction error block (614-620) through encoding a difference of the first prediction block and a first input block; encoding (620) the first encoded prediction error block into a bitstream; deriving a first reconstructed prediction error block (624) from the first encoded prediction error block; deriving a training signal (628) from one or both of the first encoded prediction error block and/or the first reconstructed prediction error block (624); retraining (630) the neural net (602) with the training signal (628) to obtain a second set of parameters for the neural net (602); deriving a second prediction block (608) at least partly based on an output of the neural net using the second set of parameters; deriving a second encoded prediction error block (614-620) through encoding a difference of the second prediction block and a second

Abstract: The embodiments relate to a method comprising receiving visual data from image capturing means, said visual data comprising a plurality of entities (510); processing the visual data to determine one or more grouping types for at least selected entities of said plurality of entities (520); storing said one or more grouping types as a metadata of a container file format, said one or more grouping types being associated with said selected entities (530); and including the metadata to a container file in association with said visual data (540).

Abstract: The invention relates to a method and technical equipment for implementing the method. The method comprises generating a three-dimensional segment of a scene of a content; generating more than one two-dimensional views of the three-dimensional segment, each two-dimensional view representing a virtual camera view; generating multi-view streams by encoding each of the two-dimensional views; encoding parameters of a virtual camera to the respective stream of the multi-view stream; receiving a selection of one or more streams of the multi-view stream; and streaming only the selected one or more streams.

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.

Abstract: The invention relates to a method comprising receiving, by a neural network, a first image comprising at least one target object; receiving, by the neural network, a second image comprising at least one query object; and determining, by the neural network, whether the query object corresponds to the target object, wherein the neural network comprises a discriminator neural network of a generative adversarial network (GAN). The invention further relates to an apparatus and a computer program product that perform the method.

Abstract: The embodiments relate to a method comprising receiving visual data in a file format compatible with ISO base media file format; processing the visual data to detect one or more content elements; storing the detected one or more content elements and information on the used process as a metadata; and including the metadata to the media file in association with the visual data. The embodiments also relate to a technical equipment for implementing the method.

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: decode encoded data to generate decoded data, the encoded data having a bitrate lower than that of original data, and extract features from the decoded data; decode encoded residual features to generate decoded residual features; and generate enhanced decoded features as a result of combining the decoded residual features with the features extracted from the decoded data.

Abstract: There are provided methods, apparatuses, systems and computer program products for coding volumetric video, where a first texture picture is coded, the first texture picture comprising a first projection of texture data of a first source volume of a digital scene model, the scene model comprising a number of further source volumes, the first projection being from the first source volume to a first projection surface, a first geometry picture is coded, the first geometry picture representing a mapping of the first projection surface to the first source volume, and first projection geometry information of the first projection is coded, the first projection geometry information comprising information of position of the first projection surface in the scene model.

Abstract: A method comprising: authoring a first section of a first media format, wherein the first section comprises type and length fields of the first section, wherein the type value of the first section of the first media format is such that allows parsers of the first media format ignore the first section; one or more entire sections complying with a second media format; and a section header of a bridge section complying with the second media format, wherein the section header comprises type and length fields; authoring a second section of the first media format, comprising type and length fields of the second section; and data complying with the second media format; and setting the content of the first section to be such that it allows parsers of the second media format ignore the type and length fields of the second section.