Abstract: Methods, apparatuses and computer program products are described for video encoding. A method can include reconstructing a 360-degree panoramic source picture for inter-layer prediction and deriving an inter-layer reference picture from the 360-degree panoramic source picture. Deriving can include upsampling at least a part of the 360-degree panoramic source picture. Upsampling can include filtering samples of a border region of the 360-degree panoramic source picture using, at least in part, one or more sample values of an opposite side border region and one or more variable values associated with one or more blocks of the opposite side border region. Deriving can include determining a reference region that crosses a picture boundary of the 360-degree panoramic source picture and including in the reference region at least one of sample values of the opposite side border region and variable values associated with blocks of the opposite side border region.

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: 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.

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 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: Described are methods, apparatuses and computer program products for signaling and storing compressed point clouds. Sub-sample entries associated with sequences of sub-samples within sequences of samples may indicate whether sequences of sub-samples were encapsulated alone in a track, without other sub-samples or additional header data. Sub-sample entry types can be indexed at track-level sub-sample description boxes. Point cloud compression coded bitstream component types may be signaled by including respective point cloud unit header information in a codec-specific parameters-related field of track level sub-sample description boxes. Sub-sample information boxes may indicate sub-sample entry indices for respective sub-samples. A flag in such information boxes may indicate the presence of sub-sample description entry indexes. Description index boxes can contain sub-sample description entry indexes in the same container as sub-sample information boxes.

Abstract: Apparatuses, methods, and computer programs for compressing a neural network are disclosed. An apparatus includes at least one processor; and at least one non-transitory memory including computer program code, the memory and the computer program code configured to, with the at least one processor, cause the apparatus to: receive information from a second device, where the information comprises at least one parameter configured to be used for compression of a neural network, where the at least one parameter is in regard to at least one first aspect or task of the neural network; and compress the neural network, where the neural network is compressed based, at least partially, upon the at least one parameter received from the second device. The apparatus may also receive a compressed neural network from the second device, and further compress the compressed neural network based on the information.

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.

Abstract: A method, apparatus and computer program product facilitate the viewing of a storyline defined in a video. In regards to a method, viewing by a user of different sequential areas of a video over time is monitored. The different sequential areas of the video over time define a storyline. If the storyline is followed, the video continues to be presented. However, if the storyline is not followed in that a next sequential area of the video is not viewed, a portion of the video prior to the next sequential area is caused to be repeatedly replayed in a loop. Following this repeated replay of the portion of the video, the repeated replay of the portion of the video is ceased and the presentation of the video is resumed if the storyline is followed and the next sequential area of the video in the storyline is viewed.

Abstract: A method, apparatus and computer program product are provided in order to create and/or decode video content of a scene that includes regions having looping video of different loop lengths with the video content of the scene being configured to be repeatedly looped, such as in the form of a cinemagraph, without any temporal discontinuity. In the context of a method, the video content of a scene is encoded. The video content includes at least two regions having looping videos of different loop lengths. The method also includes constructing metadata in association with the video content. The metadata comprises information identifying a location of each region within the scene. The metadata further comprises a loop length for each of the at least two regions. The method further includes causing provision of the video content as encoded and the metadata.

Abstract: There is disclosed a method, an apparatus, a server, a client and a non-transitory computer readable medium comprising a computer program stored therein for multi view video coding and decoding. View random access (VRA) pictures or access units are coded into a multiview bitstream. VRA pictures enable starting the decoding of a subset of the views present in the bitstream. The views selected to be accessible in VRA pictures are alternated in successive VRA pictures so that all views are gradually reconstructed when two or more VRA pictures have been decoded.

Abstract: The invention relates to concatenating or splicing of scalable video bitstreams. There are disclosed various methods, apparatuses and computer program products for video encoding and decoding and modifying coded video bitstreams. In some embodiments, indications are provided in the coded video bitstream to indicate a layer-wise decoding start-up process. These indications may be generated by encoders or splicers.

Abstract: Methods, apparatus and computer program products are provided in which a set of valid motion vector values for encoding and decoding may depend on a reference picture used. A current block of a frame is selected for encoding, and a reference block for the current block is selected. On the basis of the selected reference block a reference type is determined. On the basis of the reference type and the reference block a motion vector for the current block is determined. Motion vector information is encoded and decoded on the basis of the determined motion vector.

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: A method, apparatus and computer program product encode, into a container file comprising one or more samples, track fragment run metadata associated with a track fragment run. The track fragment run metadata includes a per-sample part comprising per-sample metadata for one or more samples in the container file and a cyclic part. The track fragment run metadata includes an indication of a pattern appearing earlier in the track fragment run and resolving the cyclic part causes at least a subset of the per-sample part to be set by cyclic assignment of the pattern indication of a pattern appearing earlier in the track fragment run.

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: There are disclosed various methods, apparatuses and computer program products for video encoding and decoding. In other embodiments, there is provided a method, an apparatus, a computer readable storage medium stored with code thereon for use by an apparatus, and a video encoder, for encoding a scalable bitstream, to provide indicating an encoding configuration, where only samples and syntax from intra coded pictures of base layer is used for coding the enhancement layer pictures. In other embodiments, there is provided an apparatus, a computer readable storage medium stored with code thereon for use by an apparatus, and a video decoder, for decoding a scalable bitstream, to receive indications of an encoding configuration, where only samples and syntax from intra coded pictures of base layer is used for coding the enhancement.

Abstract: There are disclosed various methods, apparatuses and computer program products for video encoding and decoding. In some embodiments a method comprises at least one of the following: encoding into a bitstream an indication that motion fields are stored, but only for inter-layer motion prediction; encoding into a bitstream an indication on a limited scope of motion field usage; encoding into a bitstream an indication whether or not to use the motion field for prediction; encoding into a bitstream an indication of storage parameters for storing motion information.

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 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.