Abstract: Embodiments of the invention relates to a data processing apparatus comprising a processor configured to provide a neural network, wherein the neural network comprises a neural network layer being configured to generate from an array of input data values an array of output data values based on a plurality of position dependent kernels and a plurality of input data values of the array of input data values. Moreover, embodiments of the invention relates to a corresponding data processing method.

Abstract: Embodiments of the invention relates to an apparatus for associating a video block partitioning pattern to a video coding block, wherein the apparatus comprises: an obtainer adapted to obtain values of a set of segmentation mask samples, wherein each segmentation sample of the set of segmentation mask samples represents a different position in a segmentation mask adapted to define video coding block partitions of the video coding block; a selector adapted to select a video block partitioning pattern from a predetermined group of video block partitioning patterns based on the values of segmentation mask samples of the set of segmentation mask samples; and an associator adapted to associate the selected video block partitioning pattern to the video coding block.

Abstract: The invention relates to an apparatus for decoding an encoded texture block of a texture image, the decoding apparatus comprising: a partitioner (510) adapted to determine a partitioning mask (332) for the encoded texture block (312?) based on depth information (322) associated to the encoded texture block, wherein the partitioning mask (332) is adapted to define a plurality of partitions (P1, P2) and to associate a texture block element of the encoded texture block to a partition of the plurality of partitions of the encoded texture block; and a decoder (720) adapted to decode the partitions of the plurality of partitions of the encoded texture block based on the partitioning mask.

Abstract: The disclosure relates to an apparatus for encoding an input audio signal, wherein the input audio signal comprises a plurality of input audio channels. The apparatus comprises a KLT-based pre-processor configured to transform the plurality of input audio channels into a plurality of eigenchannels and to provide metadata in the form of a plurality of metadata elements, wherein the metadata allows reconstructing the plurality of input audio channels on the basis of the plurality of eigenchannels, a metadata re-arrangement unit configured to re-arrange the plurality of metadata elements on the basis of a re-arrangement scheme into one or more metadata blocks, wherein each of the one or more metadata blocks is a multi-dimensional array, and a metadata encoder configured to encode each of the one or more metadata blocks.

Abstract: The invention relates to an apparatus for decoding an encoded texture block of a texture image, the decoding apparatus comprising: a partitioner (510) adapted to determine a partitioning mask (332) for the encoded texture block (312?) based on depth information (322) associated to the encoded texture block, wherein the partitioning mask (332) is adapted to define a plurality of partitions (P1, P2) and to associate a texture block element of the encoded texture block to a partition of the plurality of partitions of the encoded texture block; and a decoder (720) adapted to decode the partitions of the plurality of partitions of the encoded texture block based on the partitioning mask.

Abstract: The disclosure relates to an image processing apparatus for determining a depth of a pixel of a reference image of a plurality of images representing a visual scene relative to a plurality of locations, wherein the plurality of locations define a two-dimensional grid with rows and columns and wherein the location of the reference image is associated with a reference row and a reference column of the grid. The image processing apparatus comprises a depth determiner configured to determine a first depth estimate on the basis of the reference image and a first subset of the plurality of images for determining the depth of the pixel of the reference image, wherein the images of the first subset are associated with locations being associated with a row of the grid different than the reference row and with a column of the grid different than the reference column.

Abstract: A method and apparatus for encoding and decoding a texture block using depth based block partitioning, which includes an apparatus for decoding an encoded texture block of a texture image, and a partitioner, determines a partitioning mask for the encoded texture block based on depth information associated to the encoded texture block, and the partitioning mask defines a plurality of partitions and to associate a texture block element of the encoded texture block to a partition of the plurality of partitions of the encoded texture block, and a decoder decode the partitions of the plurality of partitions of the encoded texture block based on the partitioning mask.

Abstract: The disclosure relates to an image processing apparatus for selecting a plurality of depth information values for a subset of currently processed fragments of a set of currently processed fragments of a currently processed digital image. The image processing apparatus includes a non-transitory memory storage comprising instructions and one or more hardware processors in communication with the memory storage. The one or more hardware processors execute the instructions to: process the currently processed fragments of the set of currently processed fragments in parallel; and process the currently processed fragments of the subset of currently processed fragments in parallel.

Abstract: Embodiments of the invention relates to a data processing apparatus comprising a processor configured to provide a neural network, wherein the neural network comprises a neural network layer being configured to generate from an array of input data values an array of output data values based on a plurality of position dependent kernels and a plurality of input data values of the array of input data values. Moreover, embodiments of the invention relates to a corresponding data processing method.

Abstract: The present disclosure can provide an image processing apparatus. In some embodiments, the image processing apparatus in accordance with the disclosure comprises memory configured to store a previously selected depth information value (dprev), (dprev; dprevi) having been selected for a previously processed fragment and signal processing logic (103).

Abstract: The invention relates to a method (100) for coding a depth lookup table, DLT, (201, 211), the depth lookup table comprising depth value information of at least a part of a 3D picture, the method (100) comprising: selecting (101) a reference depth lookup table (203, 213); determining (103) a difference depth lookup table (205, 215) based on a comparison between depth value information of the depth lookup table to be coded (201, 211) and depth value information of the reference depth lookup table (203, 213); and coding (105) depth value information of the difference depth lookup table (205, 215) according to a predetermined coding rule.

Abstract: The disclosure relates to an apparatus for encoding an input audio signal, wherein the input audio signal comprises a plurality of input audio channels. The apparatus comprises a KLT-based pre-processor configured to transform the plurality of input audio channels into a plurality of eigenchannels and to provide metadata in the form of a plurality of metadata elements, wherein the metadata allows reconstructing the plurality of input audio channels on the basis of the plurality of eigenchannels, a metadata re-arrangement unit configured to re-arrange the plurality of metadata elements on the basis of a re-arrangement scheme into one or more metadata blocks, wherein each of the one or more metadata blocks is a multi-dimensional array, and a metadata encoder configured to encode each of the one or more metadata blocks.

Abstract: The invention relates to a method (200) for sub-range based coding a depth lookup table (300), the depth lookup table comprising depth values of a 3D video sequence, the depth values being constrained within a range (301), the method comprising: partitioning (201) the range (301) into a plurality of sub-ranges, a first sub-range (303) comprising a first set of the depth values and a second sub-range (305) comprising a second set of the depth values; and coding (203) the depth values of each of the sub-ranges of the depth lookup table (300) separately according to a predetermined coding rule.

Abstract: The disclosure relates to an image processing apparatus for selecting a plurality of depth information values for a subset of currently processed fragments of a set of currently processed fragments of a currently processed digital image. The image processing apparatus includes a non-transitory memory storage comprising instructions and one or more hardware processors in communication with the memory storage. The one or more hardware processors execute the instructions to: process the currently processed fragments of the set of currently processed fragments in parallel; and process the currently processed fragments of the subset of currently processed fragments in parallel.

Abstract: The present disclosure can provide an image processing apparatus. In some embodiments, the image processing apparatus in accordance with the disclosure comprises memory configured to store a previously selected depth information value (dprev), (dprev; dprevi) having been selected for a previously processed fragment and signal processing logic (103).

Abstract: The disclosure relates to an image processing apparatus for determining a depth of a pixel of a reference image of a plurality of images representing a visual scene relative to a plurality of locations, wherein the plurality of locations define a two-dimensional grid with rows and columns and wherein the location of the reference image is associated with a reference row and a reference column of the grid. The image processing apparatus comprises a depth determiner configured to determine a first depth estimate on the basis of the reference image and a first subset of the plurality of images for determining the depth of the pixel of the reference image, wherein the images of the first subset are associated with locations being associated with a row of the grid different than the reference row and with a column of the grid different than the reference column.

Abstract: Embodiments of the invention relates to an apparatus for associating a video block partitioning pattern to a video coding block, wherein the apparatus comprises: an obtainer adapted to obtain values of a set of segmentation mask samples, wherein each segmentation sample of the set of segmentation mask samples represents a different position in a segmentation mask adapted to define video coding block partitions of the video coding block; a selector adapted to select a video block partitioning pattern from a predetermined group of video block partitioning patterns based on the values of segmentation mask samples of the set of segmentation mask samples; and an associator adapted to associate the selected video block partitioning pattern to the video coding block.

Abstract: Embodiments provide a method for determining a corner video part of a partition of a video coding block, the video coding block comprising a plurality of video parts. The method includes selecting a video part of the video coding block according to a predetermined scanning pattern to obtain a selected video part, wherein the predetermined scanning pattern indicates a scanning order of the video parts in the video coding block. The method also includes determining whether the selected video part is arranged within the partition, and determining the selected video part as the corner video part if the selected video part is arranged within the partition.

Abstract: A method and apparatus for encoding and decoding a texture block using depth based block portioning, which includes an apparatus for decoding an encoded texture block of a texture image, and a partitioner, determines a portioning mask for the encoded texture block based on depth information associated to the encoded texture block, and the portioning mask defines a plurality of partitions and to associate a texture block element of the encoded texture block to a partition of the plurality of partitions of the encoded texture block, and a decoder decode the partitions of the plurality of partitions of the encoded texture block based on the portioning mask.

Abstract: A method for computing a synthesized picture (sT?) of a visual scene, the method comprising projecting the left depth map (sD,l) into a left projected depth map (sD,l?) and projecting the right depth map (sD,r) into a right projected depth map (sD,r?), and determining a left disoccluded area (sF,l?) in the left projected depth map (sD,l?) and a right disoccluded area (sF,r?) in the right projected depth map (sD,r?); detecting object border misalignments between the left projected depth map (sD,l?) and the right projected depth map (sD,r?); determining a left reliability map information (sR,l?) based on the left disoccluded area (sF,l?), and the detected object border misalignments, and determining a right reliability map information (sR,r?) based on the right disoccluded area (sF,r?), and the detected object border misalignments; and computing the synthesized picture.