Abstract: The embodiments relate to method for encoding and decoding, wherein the method for encoding comprises receiving an input block of a video frame for encoding; applying at least a learning-based model (702) for said input block as a processing step for encoding the block; combining (703) an output of a learning-based model with one or more data sources (712, 713) by a combination process; encoding block to a bitstream (40); using a result of the combination process as additional input for the learning-based model for encoding a subsequent block; and encoding to a bitstream combination information (720) used in the combination process, said combination information comprising at least one or more combination parameters. The embodiments also relate to technical equipment for implementing the methods.

Abstract: A method, an apparatus, and a computer program product are provided. An example method includes defining an enhancement message comprising at least one of the following: an identifying number for identifying a post-processing filter; a mode identity (idc) field used of indicating association of a post-processing filter with the identifying number; a flag for specifying the enhancement message being used for a current layer; and the payload byte comprising a bitstream; and using the enhancement message for at least one of specifying a neural network that is used as a post-processing filter or cancelling a use of a previous post-processing filter with the same identifying number.

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: The embodiments relate to a method comprising establishing a three-dimensional conversational interaction with one or more receivers; generating a pointcloud relating to a user and capturing audio from one or more audio source; generating conversational scene description comprising at least a first dynamic object describing a virtual space for the three-dimensional conversational interaction, wherein the first dynamic object refers to one or more objects specific to the three-dimensional conversational interaction, wherein said one or more objects comprises at least data relating to transformable pointcloud; audio obtained from said one or more audio source and input obtained from one or more connected devices controlling at least the pointcloud, wherein said objects are linked to each other for seamless manipulation; applying the conversational scene description into a metadata, and transmitting the metadata with the respective audio in realtime to said one or more receivers.

Abstract: The embodiments relate to a method for encoding and a decoding, and apparatuses for the same. The method for encoding comprises receiving a block of a video frame for encoding (1510); making a decision on whether or not a learning-based model is to be applied as a processing step for encoding the block (1520); applying the learning-based model for said input block according to the decision, where the learning-based model has been selectively fine-tuned according to information relating to activation of the learning-based model of previously-decoded blocks (1530); encoding a signal corresponding to the decision on usage of the learning-based model into a bitstream (1540); and encoding the block into a bitstream with an information whether the block is to be used for finetuning (1550).

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, apparatus, and computer program product are provided for training a neural network or providing a pre-trained neural network with the weight-updates being compressible using at least a weight-update compression loss function and/or task loss function. The weight-update compression loss function can comprise a weight-update vector defined as a latest weight vector minus an initial weight vector before training. A pre-trained neural network can be compressed by pruning one or more small-valued weights. The training of the neural network can consider the compressibility of the neural network, for instance, using a compression loss function, such as a task loss and/or a weight-update compression loss. The compressed neural network can be applied within a decoding loop of an encoder side or in a post-processing stage, as well as at a decoder side.

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: 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: obtaining a block of a picture or a picture in an encoder; determining if the block/picture is used for on-line learning; if affirmative, encoding the block/picture; reconstructing a coarse version of the block/picture or the respective prediction error block/picture; enhancing the coarse version using a neural net; fine-tuning the neural net with a training signal based on the coarse version; determining if the block/picture is enhanced using the neural net; and if affirmative, encoding the block/picture with enhancing using the neural net.

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 comprising: causing analysis of a portion of a visual scene; causing modification of a first sound object to modify a spatial extent of the first sound object in dependence upon the analysis of the portion of the visual scene corresponding to the first sound object; and causing rendering of the visual scene and the corresponding sound scene including of the modified first sound object with modified spatial extent.

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: This specification describes a method comprising responding to a first gesture by a first user delimiting a visual virtual reality content portion from visual virtual reality content being consumed by the first user via a first head-mounted display by selecting the delimited visual virtual reality content portion, responding to a second gesture by the first user directed towards a content consumption device associated with a second user by identifying the content consumption device as a recipient of the selected visual virtual reality content portion, and causing the selected visual virtual reality content portion to be provided to the content consumption device for consumption by t second user.

Abstract: The embodiments relate to a method comprising compressing input data (I) by means of at least a neural network (E, 310); determining a compression rate for data compression; miming the neural network (E, 310) with the input data (I) to produce an output data (c); removing a number of elements from the output data (c) according to the compression rate to result in a reduced form of the output data (me); and providing the reduced form of the output data (me) and the compression rate to a decoder (D, 320). The embodiments also relate to a method comprising receiving input data (me) for decompression; decompressing the input data (me) by means of at least a neural network (D, 320); determining a decompression rate for decompressing the input data (me); miming the neural network (D, 320) with input data (me) to produce a decompressed output data (ï); padding a number of elements to the compressed input data (me) according to the decompression rate to produce an output data (ï); and providing the output data (ï).

Abstract: There is provided an apparatus comprising means for training a neural network, wherein the training comprises applying a loss function configured to increase sparsity of a weight tensor of the neural network and to cause a plurality of non-zero elements of the weight tensor to be substantially equal to each other; and means for entropy coding the weight tensor to obtain a compressed neural network.

Abstract: Optimization of a neural network, for example in a video codec at the decoder side, may be guided to limit overfitting. The encoder may encode video(s) with different qualities for different frames in the video. Low-quality frames may be used as both input and ground-truth during optimization. High-quality frames may be used to optimize the neural network so that higher-quality versions of lower-quality inputs may be predicted. The neural network may be trained to make such predictions by making a prediction based on a constructed low-quality input for which the corresponding high-quality version is known, comparing the prediction to the high-quality version, and fine-tuning the neural network to improve its ability to predict a high-quality version of a low-quality input. To limit overfitting, the neural network may be concurrently or in an alternating fashion trained with low-quality input for which a higher-quality version of the low-quality input is known.