Abstract: A device may be configured to signal range extension profile information for coded video according to one or more of the techniques described herein.

Abstract: A method of encoding video data by an electronic device is provided. A plurality of picture parameters included in a picture header of a picture in the video data is signaled into a bitstream. A present flag included in a sub-picture header of a sub-picture generated by dividing the picture is signaled into the bitstream. The electronic device determines, based on the present flag, whether a specific one of a plurality of sub-picture parameters is determined based on the sub-picture header or the picture header. The specific one of the plurality of sub-picture parameters corresponds to the specific one of the plurality of picture parameters. The sub-picture is reconstructed based on the specific one of the plurality of sub-picture parameters when the specific one of the plurality of sub-picture parameters is determined from the sub-picture header.

Abstract: A device may be configured to perform frame rate up sampling based on information included in a neural network post-filter characteristics message. In one example, the neural network post-filter characteristics message includes a syntax element specifying a number of input pictures to be used as input for a neural network post-filter picture interpolation process and a syntax element having a value specifying a manner in which input pictures are concatenated before being input into the neural network post-filter picture interpolation process.

Abstract: A device may be configured to compress feature data according to one or more of the techniques described herein. In one example, feature data may be compressed by using residual encoding to enhance the feature data by removing redundancies. Enhanced feature data may be spatially down sampled and the number of channels of the enhanced feature data may be reduced by applying a 2D convolution operation. A heatmap based on the reduced enhanced feature data may be generated. The reduced enhanced feature data may be scaled using the generated heatmap. The scaled reduced enhanced feature data may be entropy encoded to generate a bitstream.

Abstract: A device may be configured to signal network abstraction layer unit information according to one or more of the techniques described herein.

Abstract: This disclosure relates to video coding and more particularly to techniques for signaling types of pictures for coded video. In particular, this dis-closure describes techniques for enabling and signaling a so-called gradual random access picture. According to an aspect of an invention, a second syntax element is decoded by using a value of a first syntax element wherein the first syntax element indicates a picture is a random access picture having a recovery point picture and the second syntax element specifies a first picture order count value of the recovery point picture.

Abstract: A device may be configured to determine that the neural network post-filter characteristics message provides a neural network update. In one example, a neural network post-filter characteristics message includes a syntax element having a value specifying that a post-processing filter associated with the message is a neural network identified by a specified tag Uniform Resource Identifier (URI) and neural network information URI. The neural network post-filter characteristics message further includes a syntax element having a value specifying that particular syntax elements are not present in the neural network post-filter characteristics message. Based on the values of the syntax elements it may be determined that the neural network post-filter characteristics message provides a neural network update.

Abstract: A system for retrieving watermark associated recovery data information.

Abstract: A device may be configured to generate data packets including a packet header and a payload. The packet header may include a value that signals whether the payload encapsulates input data according to a single short packet encapsulation, a single long packet encapsulation, a segmented encapsulation, or a concatenated encapsulation.

Abstract: A method for tracking a reference picture on an electronic device is described. The method includes receiving a bitstream. The method also includes decoding a portion of the bitstream to produce a decoded reference picture. The method further includes tracking the decoded reference picture in a decoded picture buffer (DPB) with reduced overhead referencing. The method additionally includes decoding a picture based on the decoded reference picture.

Abstract: A method of filtering reconstructed video data is disclosed. The method comprising: parsing a first syntax element used for setting cross-component filter coefficients; inputting a reconstructed luma picture sample array; deriving luma locations by using location corresponding to a current chroma sample; deriving a filter coefficient array by using the cross-component filter coefficients; deriving a variable by using the filter coefficient array and the reconstructed luma picture sample array defined by the luma locations; and deriving a scaled variable by using the variable, wherein the variable is modified by a sum of a sample of a current chroma block, which is defined by a predetermined location, and the scaled variable.

Abstract: An electronic device for encoding a picture is described. The electronic device includes a processor and instructions stored in memory that are in electronic communication with the processor. The instructions are executable to encode a step-wise temporal sub-layer access (STSA) sample grouping. The instructions are further executable to send and/or store the STSA sample grouping.

Abstract: A device may be configured to signal sequence parameter information according to one or more of the techniques described herein. The sequence parameter set information may include in its second byte a syntax element specifying a chroma sampling relative to a luma sampling and a syntax element specifies a luma coding tree block size of each coding tree unit.

Abstract: A device may be configured to signal neural network post-filter parameter information. In one example, a device signals a neural network post-filter characteristics message including a syntax element specifying a number of interpolated pictures generated by a post-processing filter between consecutive pictures used as input for the post-processing filter. In one example, a neural network post-filter characteristics message includes a syntax element specifying a number of decoded output pictures used as input for the post-processing filter.

Abstract: A method of decoding video data includes receiving a first decoding unit information message corresponding to a first decoding unit of a current access unit, determining a syntax element used to compute a decoded picture buffer output time of the current access unit is not present in the first decoding unit information message, and based on the syntax element not being present in the first decoding unit information message, inferring the value of the syntax element to be equal to a value of a corresponding instance of the syntax element in a second decoding unit information message, wherein the second decoding unit information corresponds to a second decoding unit belonging to the current access unit.

Abstract: A method and a receiver for receiving a recovery file format file from a provider comprising the steps of: (a) receiving a recovery data table including a RecoveryDataTable element; (b) receiving a contentID field of said RecoveryDataTable element describing a type of content identifier provided in a message having a cardinality of 0 . . . N; (c) receiving a svcInetUrl field of said RecoveryDataTable element describing service information; (d) receiving a URLValue field of said svcInetUrl field describing URL to access Internet signaling files for said service information; (e) decoding elements of said file based upon said recovery data table.

Abstract: A method for determining a reference index for a reference picture list is disclosed. A reference picture list structure in one of a sequence parameter set and a slice header is decoded. A reference index for the reference picture list structure is derived according to a value of a reference picture list flag. A number of reference index active syntax in the slice header is decoded, if a number of entries in the reference picture list structure is greater than 1. The number of reference index active syntax is defined for i. A variable is derived by adding one to a value of the number of reference index active syntax. A value subtracted one from a value of the variable specifies a maximum reference index for the reference picture list.

Abstract: This disclosure relates to video coding and more particularly to a method of decoding network abstraction layer (NAL) unit information. The method of decoding NAL unit information comprises: receiving a NAL unit header syntax structure having two bytes; and decoding a first 1-bit syntax element, a second 1-bit syntax element and a 6-bit syntax element in the NAL unit header syntax structure, wherein a value of the first 1-bit syntax element is equal to zero, a value of the second 1-bit syntax element is equal to zero, and the 6-bit syntax element specifies an identifier of a layer to which a VCL NAL unit belongs or an identifier of a layer to which a non-VCL NAL unit applies.

Abstract: A device may be configured to signal hypothetical reference decoder parameters according to one or more of the techniques described herein.

Abstract: A device may be configured to general constraint information according to one or more of the techniques described herein.