Abstract: Embodiments are related to an image filter configured to: obtain a picture; perform a first and second sample-wise classification of the picture; select, sample-wise, first convolution kernels from a first set of convolution kernels, based on the first classification; and second convolution kernels from a second set of convolution kernels, based on the second classification; perform, in one or more convolution layers of the image filter, on the picture or on a pre-processed version of the picture, a sequence of one or more first convolutions using the selected first convolution kernels, in order to provide a plurality of first convolution outputs and a sequence of one or more second convolutions using the selected second convolution kernels, in order to provide a plurality of second convolution output; and combine the first and second convolution outputs, in order to obtain a plurality of combined convolution outputs.

Abstract: A method for checking a video data stream having a video encoded thereinto on trustworthiness comprises: subjecting a predetermined portion of the video data stream, or data derived therefrom, to a hash function to obtain a hash value; deriving a digital signature from the video data stream; and checking whether the hash value fits to the digital signature to determine whether the video data stream is trustworthy.

Abstract: A video encoder for encoding a video into a data stream using motion compensated prediction for inter predicted blocks, comprising a hypothesis number control, configured to control a number of prediction hypotheses of the inter predicted blocks within a predetermined portion of the video to meet a predetermined criterion.

Abstract: Apparatuses and methods for checking a data stream on trustworthiness are described. According to an aspect, the data stream indicates, whether a segment is a first segment or whether a segment is a last segment of assigned sequence of segments. According to another aspect, an apparatus for decoding a data stream is configured for deriving, from the data stream, whether a verification chain within a temporal sequence of segments is interrupted at a segment.

Abstract: A method for checking a video data stream having a video encoded thereinto on trustworthiness comprises: subjecting a predetermined portion of the video data stream, or data derived therefrom, to a hash function to obtain a hash value; deriving a digital signature from the video data stream; and checking whether the hash value fits to the digital signature to determine whether the video data stream is trustworthy.

Abstract: An apparatus for decoding a picture from a binary representation of the picture is configured for reconstructing, based on the binary representation, samples of the picture; and for classifying the reconstructed samples for an adaptive in-loop filtering, ALF, using a soft classification such as a convolutional neural network, CNN.

Abstract: A block-based codec using transform-based residual coding is described wherein a current transform coefficient of a set of transform coefficients is predicted based on a function, attributes of which have values of previously en/decoded samples neighboring the predetermined block, and if the current transform coefficient is not firstly en/decoded among the set of transform coefficients, one or more previously en/decoded transform coefficients among the set of transform coefficients. Further, a block-based codec is described where the set may have merely one transform coefficient, and one where the transform is improved by computing an additive offset mask for the transform using an improvement function, attributes of which have the transform and the predicted sample filling. The described aspects may be combined.

Abstract: The application describes an apparatus for further training a pre-trained version of a decoder fitting to a variational picture autoencoder, the decoder having a hyperdecoder for deriving statistical entropy-coding parameters from a quantized hyperprior in a data stream, an entropy decoder for decoding quantized latents from the data stream using the statistical entropy-coding parameters, and a latents-to-picture decoder for deriving from the quantized latents a decoded picture, the apparatus configured to provide a training set of training data elements corresponding to a set of various test pictures, each training data element having quantized latents resulting from applying the variational picture autoencoder to an associated test picture, and train the latents-to-picture decoder on the training set with respect to distortion optimization to obtain a further trained version of the latents-to-picture decoder. Further, another variant trains the hypercoder system.

Abstract: In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.

Abstract: A method for checking a video data stream having a video encoded thereinto on trustworthiness comprises: subjecting a predetermined portion of the video data stream, or data derived therefrom, to a hash function to obtain a hash value; deriving a digital signature from the video data stream; and checking whether the hash value fits to the digital signature to determine whether the video data stream is trustworthy.

Abstract: An apparatus for decoding a data structure from a data stream is configured for sequentially reconstructing a set of features, wherein the apparatus is configured for reconstructing a feature of the set of features by deriving a quantization index from the data stream using arithmetic decoding; mapping the quantization index to a reconstruction value in dependence on a quantization state, and assigning the reconstruction value to the feature; updating the quantization state in dependence on the quantization index and the quantization state; and deriving the data structure based on the set of features. The apparatus is configured for deriving probabilities for the arithmetic decoding of the quantization index in dependence on the quantization state.

Abstract: Some embodiments relate to a method, a decoder and/or an encoder for entropy coding of parameters of neural networks and their incremental updates, and in particular to reduced value set coding and history depended significance coding.

Abstract: The application of coded subblock flags is performed differently between the case of applying an identity transform to a currently coded transform block on the one hand and applying a non-identity transform to the currently coded transform block on the other hand, in a manner yielding improved coding efficiency.

Abstract: A video encoder for encoding a video into a data stream using motion compensated prediction for inter predicted blocks, comprising a hypothesis number control, configured to control a number of prediction hypotheses of the inter predicted blocks within a predetermined portion of the video to meet a predetermined criterion.

Abstract: A method for checking a video data stream having a video encoded thereinto on trustworthiness comprises: subjecting a predetermined portion of the video data stream, or data derived therefrom, to a hash function to obtain a hash value; deriving a digital signature from the video data stream; and checking whether the hash value fits to the digital signature to determine whether the video data stream is trustworthy.

Abstract: A video decoder includes one or more processors that are configured to: determine that a picture is in a 4:4:4 color sampling format, determine, based at least in part on an index signaled in a data stream, a matrix-based intra prediction (MIP) mode, decode a luma block of the picture using the MIP mode, determine, for a chroma block of the picture, whether a coding tree of the chroma block is a single tree, select an intra prediction mode for decoding the chroma block, and decode the chroma block using the selected intra prediction mode. The selected intra prediction mode is the MIP mode in response to the coding tree of the chroma block being the single tree, and the selected intra prediction mode is a planar intra prediction mode in response to the coding tree of the chroma block not being the single tree.

Abstract: Apparatuses and methods for checking a data stream on trustworthiness are described. According to an aspect, the data stream indicates, whether a segment is a first segment or whether a segment is a last segment of assigned sequence of segments. According to another aspect, an apparatus for decoding a data stream is configured for deriving, from the data stream, whether a verification chain within a temporal sequence of segments is interrupted at a segment.

Abstract: An apparatus for checking a video data stream on trustworthiness derives a number of substreams of a predetermine temporal segment out of a sequence of temporal segments, in units of which the video data stream is checkable on trustworthiness, and further derives dependency information, which indicates, for the substream, whether the substream is dependent or whether the substream depends on one or more reference substreams. The trustworthiness check is performed by forming a verification stream based on a hash value, which is obtained from a portion of the substream to be verified and based on a reference hash value. If the substream is independent, a hash value derived for a corresponding substream of the preceding temporal segment is used as the reference hash value.

Abstract: A previously encoded or reconstructed version of a neighborhood of a predetermined block to be predicted is exploited so as to result into a more efficient predictive coding of the prediction block. In particular, a spectral decomposition of a region composed of this neighborhood and a first version of a predicted filling of the predetermined block results into a first spectrum which is subject to noise reduction and the thus resulting second spectrum may be subject to a spectral composition, thereby resulting in a modified version of this region including a second version of the predicted filling of the predetermined block. Owing to the exploitation of the already processed, i.e. encoded/reconstructed, neighborhood of the predetermined block, the second version of the predicted filling of the predetermined block tends to improve the coding efficiency.

Abstract: An apparatus for checking a video data stream on trustworthiness derives a number of substreams of a predetermine temporal segment out of a sequence of temporal segments, units of which the video data stream is checkable on trustworthiness, and further derives dependency information, which indicates, for the substream, whether the substream is dependent or whether the substream depends on one or more reference substreams. The trustworthiness check is performed by forming a verification stream based on a hash value, which is obtained from a portion of the substream to be verified and based on a reference hash value. If the substream is independent, a hash value derived for a corresponding substream of the preceding temporal segment is used as the reference hash value.