Abstract: Various embodiments provide an apparatus, a method and a computer program product for end-to-end learned predictive coding of media frames. An example 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 one or more media frames for at least one neural network; wherein an inter-frame codec is applied to at least one media frame of the one or more media frames; and wherein a first decoded reference frame and a second decoded reference frame refer to reference frames for the at least one media frame.

Abstract: An example method includes: receiving an input extended block comprising an input block and input margins, wherein the input block is derived from an image or a video frame, and wherein the input block and the input margins are input to a filter, and wherein the input margins comprise pixels of the image or the video frame; filtering the input extended block to obtain a filtered extended block comprising a filtered block and filtered margins; receiving other blocks, wherein the other blocks are derived from the image or video frame, and wherein at least one pixel of the other blocks overlaps with at least one pixel of the filtered margins of the filtered extended block; and blending the filtered extended block with the other blocks, wherein an operation to blend the filtered extended block with the other blocks is applied to two or more overlapping pixels

Abstract: A method is provided for computing predetermined loss terms based on original data and decoded data; training one or more neural networks of a system by using the predetermined loss terms; updating weights for one or more of other loss terms; and determining trade-offs between predetermined objectives of the system. Corresponding apparatuses and computer program products are also provided.

Abstract: A method comprising: determining a first sample in an input color space (500); determining a component of the input color space that the first sample represents (502); determining a pre-quantizer based on the determined component (504); quantizing the first sample using the determined pre-quantizer (506); and encoding the first sample value with video or image coding means (508).

Abstract: The embodiments relate to a method and a technical equipment for implementing the method. The method includes receiving a picture to be encoded; performing at least one prediction according to a first prediction mode for samples inside a block of the picture in a current channel; deriving an intra prediction mode from at least one coded block in a reference channel; performing at least one other prediction according to the derived intra prediction mode for the samples inside the block of the picture; and determining a final prediction of the block based on said at least one first and at least one second predictions with weights.

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 comprising 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: organize plurality of decoders side neural networks based on one or more task categories or one or more tasks; and select a decoder side neural network based at least on the one or more task categories or the one or more task.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example apparatus includes at least one processor; and at least one non-transitory memory comprising 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 iteratively perform following until a stopping criterion is met: provide a finetuning driving content (FDC) or a content derived from FDC to a decoder side neural network (DSNN); compute an output of the DSNN as a processed FDC; compute a loss based on the processed FDC and an approximated ground truth data (AGT) associated with the FDC; compute an update to the DSNN; and apply the computed update to the DSNN.

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: An apparatus, a method and a computer program product are described comprising: obtaining or receiving video data; providing a current frame and/or one or more previous frames of the obtained or received video data to an input of a neural network; generating a predicted output at an output of the neural network, wherein the predicted output comprises at least one of one or more predicted future frames of the video data and predicted properties of one or more future frames of the video data; determining one or more processing decisions based, at least in part, on the predicted output; and processing the current frame of the video data at least partially according to the one or more processing decisions.

Abstract: A method comprising: decoding, from a bitstream, a first encoded region of first picture into a first preliminary reconstructed region; forming a first reconstructed region from the first preliminary reconstructed region, wherein the forming comprises resampling and/or rearranging the first preliminary reconstructed region, wherein the rearranging comprises relocating, rotating and/or mirroring; and decoding at least a second region, wherein the first reconstructed region is used as a reference for prediction in decoding the at least second region and the second region either belongs to a second picture and is spatially collocated with the first reconstructed region or belongs to the first picture.

Abstract: There are disclosed various methods, apparatuses and computer program products for video encoding and decoding. In some embodiments a first reconstructed picture is interpreted as a first three-dimensional picture in a coordinate system. A rotation is obtained and the first three-dimensional picture is projected (612, 614) onto a first geometrical projection structure (613, 615), the geometrical projection structure having an orientation according to the rotation within the coordinate system. A first reference picture is formed (616) by unfolding the first geometrical projection structure into a second geometrical projection structure, and at least a block of a second reconstructed picture is predicted from the first reference picture.

Abstract: A method comprising: decoding, from a bitstream, a first encoded region of first picture into a first preliminary reconstructed region; forming a first reconstructed region from the first preliminary reconstructed region, wherein the forming comprises resampling and/or rearranging the first preliminary reconstructed region, wherein the rearranging comprises relocating, rotating and/or mirroring; and decoding at least a second region, wherein the first reconstructed region is used as a reference for prediction in decoding the at least second region and the second region either belongs to a second picture and is spatially collocated with the first reconstructed region or belongs to the first picture.