Abstract: An image prediction method according to the present invention may comprise: identifying a reference pixel region designated for obtaining correlation information; determining a reference pixel processing configuration on the basis of determination of the availability of the reference pixel region; and performing intra prediction according to the determined reference pixel processing. As described above, performing intra prediction on the basis of the availability of a reference pixel according to the present invention can improve encoding performance.

Abstract: Systems, methods, and instrumentalities are disclosed that relate to the processing of a media container file associated with 3D video data. The media container file may indicate that certain video-based point cloud compression (V-PCC) component tracks may be played together as a playout group. These V-PCG component tracks may represent respective encoded versions of one or more V-PCC components, and a video decoding device may play the tracks together in response to determining that the tracks belong to the same playout track group. The video decoding device may also determine from the media container file that certain PCC component tracks include tile groups that correspond to different objects in a point cloud or different parts of a same object in the point cloud. The video decoding device may decode these tile groups independently from each other so that a subset of the objects or parts of the point cloud may be accessed without also accessing the rest of the objects or parts.

Abstract: Systems and methods provide editing operations in a smart editing system that may generate a focal point within a mask of an object for each frame of a video segment and perform editing effects on the frames of the video segment to quickly provide users with natural video editing effects. An eye-gaze network may produce a hotspot map of predicted focal points in a video frame. These predicted focal points may then be used by a gaze-to-mask network to determine objects in the image and generate an object mask for each of the detected objects. This process may then be repeated to effectively track the trajectory of objects and object focal points in videos. Based on the determined trajectory of an object in a video clip and editing parameters, the editing engine may produce editing effects relative to an object for the video clip.

Abstract: A method of point cloud data processing includes determining a 3D region of a point cloud data and a 2D region of a point cloud track patch frame onto which one or more points of the point cloud data are projected; and reconstructing, based on patch frame data of the a point cloud track included in the 2D region and video frame data of corresponding point cloud component tracks, the 3D region of the point cloud data.

Abstract: A video transmission method according to embodiments may comprise the steps of: encoding video data; and transmitting the video data. A video reception method according to embodiments may comprise the steps of: receiving video data; and decoding the video data.

Abstract: A device for processing point cloud data according to embodiments may comprise the steps of: encoding point cloud data including geometry information and attribute information; and transmitting a bitstream including the encoded point cloud data.

Abstract: A three-dimensional data encoding method includes: generating pieces of encoded data by encoding subspaces obtained by dividing a current space including three-dimensional points; and generating a bitstream including the pieces of encoded data and pieces of first information each of which corresponds to a corresponding one of the subspaces. Each of the pieces of first information indicates whether the bitstream includes second information indicating a structure of the corresponding one of the subspaces.

Abstract: A method for lossy video encoding, transmission and decoding, the method comprising the steps of: receiving a first frame and a second frame at a first computer system; determining a first flow between the first frame and the second frame; determining a second flow based on the first frame and the second frame; encoding an input based on the first flow and the second flow using a first trained neural network to produce a latent representation; transmitting the latent representation to a second computer system; decoding the latent representation using a second trained neural network to produce an output flow; and using the output flow to obtain an output frame, wherein the output frame is an approximation of the second frame.

Abstract: Methods and devices for encoding and decoding data representative of a 3D scene are disclosed. A set of first patches is generated from a first MVD content acquired from a first region of the 3D scene. A patch is a part of one of the views of the MVD content. A set of second patches is generated from a second MVD content acquired from a second region of the 3D scene. An atlas packing first and second patches is generated and associated with metadata indicating, for a patch of the atlas, whether the patch is a first or a second patch At the decoding side, first patches are used for rendering the viewport image and second patches are used for pre-processing or post-processing the viewport image.

Abstract: Methods and apparatus for processing of volumetric visual data are described. One example method includes decoding, by a decoder, a bitstream containing volumetric visual information for a 3-dimensional scene that is represented as one or more atlas sub-bitstreams and one or more encoded video sub-bitstreams, reconstructing, using a result of decoding the one or more atlas sub-bitstreams and a result of decoding the one or more encoded video sub-bitstreams, the 3-dimensional scene, and rendering a target view of the 3-dimensional scene based on a desired viewing position and/or a desired viewing orientation.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. The encoder is configured to convert a point cloud into an image based representation. The encoder packs patch images into an image frame and fills empty spaces in the image frame with a padding. The encoder is also configured to determine quantized minimum depths and/or maximum depths patch images in the image frames, wherein depth information is signaled relative to the quantized minimum depth.

Abstract: A system and method for translating a 2D image to a 3D image is provided. A 2D image having pixels grouped into tiles is obtained. Contour lines associated with an altitude value are located on the 2D image. The altitude values are determined. Each tile in the 2D image is represented using at least one voxel. A height map of the voxels is generated based on the contour lines and altitude values as a base layer for a 3D image. A terrain type of each of the voxels of the 3D image is determined and objects are placed in the 3D image. The 3D image is output.

Abstract: An image decoding method according to the present invention may include splitting a picture into a plurality of tiles; and determining at least one slice on the basis of the plurality of tiles. Here, splitting a picture into a plurality of tiles may include: determining the width of a first tile column in the picture; and determining the width of a second tile column neighboring the first tile column.

Abstract: A video signal decoding device comprises a processor, wherein: the processor decodes a sequence parameter set (SPS) raw byte sequence payload (RBSP) syntax included in a bitstream of a video signal, and decodes the bitstream on the basis of the decoding result of the SPS RBSP syntax; the SPS RBSP syntax includes a first syntax element related to the number of one or more sub-pictures configuring one picture, and a second syntax element indicating whether to process a boundary of the one or more sub-pictures as a boundary of the one picture on the basis of the first syntax element; and the second syntax element is parsed only when the number of the one or more sub-pictures is two or more.

Abstract: Methods, systems and apparatus for processing of volumetric media data are described. One example method of volumetric media determining, from a media presentation description (MPD) file, one or more preselection elements corresponding to a preselection of a volumetric media, accessing, using the one or more preselection elements, one or more atlas data components and associated video-encoded components of the volumetric media; and reconstructing the volumetric media from the one or more atlas data components and the associated video-encoded components.

Abstract: Disclosed herein are a point cloud data transmission method including encoding point cloud data, and transmitting point cloud data, and a point cloud data reception method including receiving point cloud data, decoding the point cloud data, and rendering the point cloud data.

Abstract: In a data processing method for an immersive media, independently coded region description information of an independently coded region of the immersive media is acquired. The independently coded region corresponds to a segmented video of a plurality of segmented videos encapsulated in tracks of a same track group. The independently coded region description information includes an independently coded region information and coordinate information. The coordinate information includes coordinate system identification information that indicates a coordinate system of the independently coded region. Further, the segmented video of the immersive media is displayed according to the independently coded region description information. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Abstract: A system for extracting a product information of assets from the low resolution media contents taken in an environment 104 and updating a global product-master database 110 with the extracted product information is provided. An image capturing device 102 captures the media contents of assets. The product information extraction system 106 that (i) receives the media contents from the device 102, (ii) identifies the low resolution media contents based on size and dimensions of media contents, (iii) parses the low resolution media contents, using a system of cascading deep neural networks, to generate the product information at Stock Keeping Unit (SKU) level, (iv) transfers the product information obtained from the deep neural network system to the point of sale device 108 to update a local point-of-sale product-master, and (v) transmits the product information to the a global product-master server to update the global product-master database 110.

Abstract: Provided is a generation unit that generates an identification region map indicating whether or not each divided object data is visible from each position in a three-dimensional space by using information regarding orientation of a normal vector dividing an object in the three-dimensional space and information regarding an outline of the object.

Abstract: An image prediction method according to the present invention may comprise: identifying a reference pixel region designated for obtaining correlation information; determining a reference pixel processing configuration on the basis of determination of the availability of the reference pixel region; and performing intra prediction according to the determined reference pixel processing. As described above, performing intra prediction on the basis of the availability of a reference pixel according to the present invention can improve encoding performance.

Abstract: A system for updating/magnifying regions within one or more data frames containing a region of interest while regions outside the region of interest are not updated or are updated less frequently. Edge devices are thereby able to surgically apply super-resolution algorithms to relevant regions of image frames, thereby leveraging their overall effectiveness.

Abstract: According to the disclosure of the present document, for LMCS, a linear reshaper may be used, LMCS codewords (or ranges thereof) may be restricted, and in the chroma scaling of the LMCS, a single chroma residual scaling factor may be used. Accordingly, the resources/cost (of software or hardware) necessary for an LMCS procedure may be minimized, and latency in coding may be eliminated, thus enabling the LMCS procedure to be efficiently performed.

Abstract: The present disclosure relates to an information processing apparatus and an information generation method that enable suppression of deterioration in subjective quality of a point cloud. There is generated an occupancyMap indicating, for each local area of a frame image, presence or absence of a projection image of a point cloud on a two-dimensional plane in accordance with a positional relationship of points in a three-dimensional space, while the point cloud represents an object having a three-dimensional shape as a set of the points. The present disclosure can be applied to, for example, an information processing apparatus, an encoding device, a decoding device, or the like.

Abstract: A three-dimensional data encoding method encodes a plurality of three-dimensional points, and includes: selecting one of two or more prediction modes for calculating a predicted value of an attribute information item of the first three-dimensional point, in accordance with attribute information items of one or more second three-dimensional points in the vicinity of a first three-dimensional point; calculating the predicted value by the selected prediction mode; calculating, as a prediction residual, a difference between a value of the attribute information item of the first three-dimensional point and the calculated predicted value; and generating a bit stream that includes the one prediction mode and the prediction residual.

Abstract: Methods, apparatus, systems and articles of manufacture for video coding using object metadata are disclosed. An example apparatus includes an object separator to separate input views into layers associated with respective objects to generate object layers for geometry data and texture data of the input views, a pruner to project the first object layer of a first basic view of the at least one basic views against the first object layer of a first additional view of the at least one additional views to generate a first pruned view and a first pruning mask, a patch packer to tag a patch with an object identifier of the first object, the patch corresponding to the first pruning mask, and an atlas generator to generate at least one atlas to include in encoded video data, the atlas including the patch.

Abstract: Encoding or decoding picture information can involve determining a first scaling factor varying with a first granularity to scale a chroma prediction residual associated with chroma information included in the picture information; determining a second scaling factor varying with a second granularity finer than the first granularity; scaling the chroma prediction residual based on a combination of the first scaling factor and the second scaling factor to provide a scaled chroma prediction residual with the second granularity; and encoding or decoding at least a portion of the picture information based on the scaled chroma prediction residual.

Abstract: An image encoding/decoding method and apparatus are provided. The image decoding method includes obtaining, from a bitstream, network abstraction layer (NAL) unit type information of at least one NAL unit including coded image data, determining at least one NAL unit type of one or more slices in the current picture based on the obtained NAL unit type information, and decoding the current picture based on the determined NAL unit type. The current picture is determined to be a random access skipped leading (RASL) picture, based on the determined NAL unit type including a RASL picture NAL unit type (RASL_NUT). When an intra random access point (IRAP) picture associated with the RASL picture is a first picture in decoding order, the RASL picture is decoded, based on the RASL picture including one or more slices having a random access decodable leading (RADL) picture NAL unit type (RADL_NUT).

Abstract: Apparatus comprises video data decoder circuitry configured to decode an input video data stream, the video data decoder being responsive to parameter data associated with the input video data stream, the parameter data indicating a profile selected from a plurality of profiles, each profile defining a decoding attribute comprising one or more of a bit depth and a chrominance subsampling format; detector circuitry configured to detect constraint data associated with the input video data stream, the constraint data defining a difference between a decoding attribute applicable to the input video data stream and the decoding attribute defined by the profile indicated by the parameter data, in which the constraint data is configured to indicate a zero difference of the decoding attribute by a zero value of the constraint data; and control circuitry configured to control the video data decoder to decode the input video data stream to generate a decoded video data stream having a decoding attribute defined by the e

Abstract: Systems and methods are described for enabling a consumer of streaming video to obtain different views of the video, such as zoomed views of one or more objects of interest. In an exemplary embodiment, a client device receives an original video stream along with data identifying objects of interest and their spatial locations within the original video. In one embodiment, in response to user selection of an object of interest, the client device switches to display of a cropped and scaled version of the original video to present a zoomed video of the object of interest. The zoomed video tracks the selected object even as the position of the selected object changes with respect to the original video. In some embodiments, the object of interest and the appropriate zoom factor are both selected with a single expanding-pinch gesture on a touch screen.

Abstract: A method and Video-Based Point Cloud Compression (V-PCC) decoder for synchronization of decoded frames before point cloud reconstruction is provided. A V-PCC bit-stream which includes encoded frames associated with a point cloud sequence is received. Sub-streams of the received V-PCC bit-stream are decoded by a group of video decoders of the V-PCC decoder to generate V-PCC components, such as an attribute component, a geometry component, an occupancy map component, and an atlas component. A release of the attribute component, the geometry component, the occupancy map component, and the atlas component to the reconstruction unit is delayed based on a first output delay, a second output delay, a third output delay, and a fourth output delay, respectively. The delayed release synchronizes the attribute component, the geometry component, the occupancy map component, and the atlas component with each other before the reconstruction unit reconstructs a point cloud based on the V-PCC components.

Abstract: An example device for decoding point cloud data includes memory configured to store the point cloud data and one or more processors implemented in circuitry and coupled to the memory. The one or more processors are configured to determine dimensions of a region box and determine dimensions of a slice bounding box. The one or more processors are also configured to decode a slice of the point cloud data associated with the slice bounding box. The dimensions of the region box are constrained to not exceed the dimensions of the slice bounding box.

Abstract: The present invention relates to an ultrasound imaging system (100) for producing spatially compounded 3D ultrasound image data, comprising: —an ultrasound acquisition unit (16) for acquiring a plurality of 3D ultrasound image data having different but at least partially overlapping field of views, —a tracking unit (62) adapted to determine a relative spatial position of each of the plurality of 3D ultrasound image data with respect to each other, and —a stitching unit (64) adapted to compound the plurality of 3D ultrasound image data by stitching them to each other in order to generate compounded 3D ultrasound image data, wherein the stitching unit (64) is adapted to calculate a stitching order of the plurality of 3D ultrasound image data based on the determined relative spatial position of the 3D ultrasound image data by minimizing an overlapping area of the different field of views of the plurality of 3D ultrasound image data, and wherein stitching unit (64) is adapted to stitch the plurality of 3D ultraso

Abstract: An image decoding method according to the present invention may include splitting a picture into a plurality of tiles; and determining at least one slice on the basis of the plurality of tiles. Here, splitting a picture into a plurality of tiles may include: determining the width of a first tile column in the picture; and determining the width of a second tile column neighboring the first tile column.

Abstract: A wireless device (100) is configured for dual mode V2X communications over multiple short range radio interfaces. The wireless device (100) is configured to transmit ITS messages over a first short range radio interface configured to operate according to a first communication standard (e.g. PC5 or IEEE 802.11p), and to receive ITS messages over both the first short range radio interface and a second short radio interface configured to operate according to a second communication standard. Implementing the transmitter chain of only one technology, either PC5 or IEEE 802.11p, at each wireless device (100) reduces complexity and mitigates co-channel and adjacent channel interference that is caused by uncoordinated and concurrent transmissions of different technologies from the same wireless device. Implementing receiver chains for both PC5 and 802.11p allows the wireless device (100) to receive signals in the ITS frequency band regardless of which technology the transmitting device is using.

Abstract: A program map table in a transport stream comprising an elementary stream identifier indicating a particular elementary stream, a high dynamic range flag indicating the presence or absence of high dynamic range content within the elementary stream, and a wide color gamut flag indicating the presence or absence of wide color gamut content within the elementary stream.

Abstract: A method for encoding a video image using coding parameters, adapted on the basis of motion of the video image and of an output of a machine-learning based model, wherein the machine-learning based model is input with samples of a block of the video image and motion information of the samples, and along with texture, wherein the machine-learning model segments the video image into regions based on strength of the motion determined from the motion information. An object is detected within the video based on the motion and the texture, and spatial-time coding parameters are determined based on the strength of the motion, and whether or not the detected objects moves.

Abstract: Video coding may include generating, by a processor, a decoded frame by decoding a current frame from an encoded bitstream and outputting a reconstructed frame based on the decoded frame. Decoding includes identifying a current encoded block from the current frame, identifying a prediction coding model for the current block, wherein the prediction coding model is a machine learning prediction coding model from a plurality of machine learning prediction coding models, identifying reference values for decoding the current block based on the prediction coding model, obtaining prediction values based on the prediction coding model and the reference values, generating a decoded block corresponding to the current encoded block based on the prediction values, and including the decoded block in the decoded frame.

Abstract: Described is picture segmentation through columns and slices in video encoding and decoding. A video picture is divided into a plurality of columns, each column covering only a part of the video picture in a horizontal dimension. All coded tree blocks (“CTBs”) belonging to a slice may belong to one or more columns. The columns may be used to break the same or different prediction or in-loop filtering mechanisms of the video coding, and the CTB scan order used for encoding and/or decoding may be local to a column. Column widths may be indicated in a parameter set and/or may be adjusted at the slice level. At the decoder, column width may be parsed from the bitstream, and slice decoding may occur in one or more columns.

Abstract: A system includes at least one imaging sensor and a processor. The processor is configured to acquire, using the imaging sensor, detected data describing an environment of an autonomous vehicle. The processor is further configured to derive reference data, which describe the environment, from a predefined map, to compute difference data representing a difference between the detected data and the reference data, and to transfer the difference data. Other embodiments are also described.

Abstract: A video signal decoding device comprises a processor, wherein: the processor decodes a sequence parameter set (SPS) raw byte sequence payload (RBSP) syntax included in a bitstream of a video signal, and decodes the bitstream on the basis of the decoding result of the SPS RBSP syntax; the SPS RBSP syntax includes a first syntax element related to the number of one or more sub-pictures configuring one picture, and a second syntax element indicating whether to process a boundary of the one or more sub-pictures as a boundary of the one picture on the basis of the first syntax element; and the second syntax element is parsed only when the number of the one or more sub-pictures is two or more.

Abstract: An decoding device, an encoding device and a method for point cloud encoding is disclosed. The method includes generating, from a three-dimensional point cloud, multiple two-dimensional frames, the two-dimensional frames including at least a first frame representing a geometry of points in the three-dimensional point cloud and a second frame representing texture of points in the three-dimensional point cloud. The method also includes generating an occupancy map indicating locations of pixels in the two-dimensional frames that represent points in the three-dimensional point cloud. The method further includes encoding the two-dimensional frames and the occupancy map to generate a compressed bitstream. The method also includes transmitting the compressed bitstream.

Abstract: An apparatus for multi-bitrate content streaming includes a receiving module configured to capture media content, a streamlet module configured to segment the media content and generate a plurality of streamlets, and an encoding module configured to generate a set of streamlets. The system includes the apparatus, wherein the set of streamlets comprises a plurality of streamlets having identical time indices and durations, and each streamlet of the set of streamlets having a unique bitrate, and wherein the encoding module comprises a master module configured to assign an encoding job to one of a plurality of host computing modules in response to an encoding job completion bid. A method includes receiving media content, segmenting the media content and generating a plurality of streamlets, and generating a set of streamlets.

Abstract: A conference device comprising a first image sensor for provision of first image data, a first image processor configured for provision of a first primary videostream and a first secondary videostream based on the first image data, an intermediate image processor in communication with the first image processor and configured for provision of a field-of-view videostream and a region-of-interest videostream, wherein the field-of-view videostream is based on the first primary videostream, and the region-of-interest videostream is based on the first secondary videostream, and an output processor configured to determine first image control data based on the field-of-view videostream and transmit the first image control data to the first image processor, wherein the first image processor is configured for provision of the first secondary videostream based on the first image control data.

Abstract: A method for encoding a video sequence in a video encoder is provided that includes adapting a quantization parameter of a block of pixels in a picture of the video sequence based on a transform block size of the block of pixels to determine a final quantization parameter, and quantizing transform coefficients of the block of pixels using the final quantization parameter.

Abstract: Described is a computer-implemented method for determining uncertainties in measurement data from a measurement of an object, wherein a digital representation of the object is generated by the measurement. The object representation has items of image information, which each indicate a value of a measurement variable for the object at a defined position of the object. Statistical noise is superimposed on the image information. The method includes determining the object representation, determining a distance field from the image information relating to the object representation, determining a strength of the statistical noise in the image information, determining an uncertainty of the distance values of the distance field on the basis of the strength of the statistical noise, and determining an uncertainty of the position of at least one point on at least one material boundary surface from the uncertainty of the distance values of the distance field.

Abstract: A system comprises an encoder configured to compress attribute information and/or spatial information for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. The encoder is configured to convert a point cloud into an image based representation. The encoder packs patch images into an image frame and fills empty spaces in the image frame with a padding. The encoder is also configured to determine quantized minimum depths and/or maximum depths patch images in the image frames, wherein depth information is signaled relative to the quantized minimum depth.

Abstract: Systems and methods for decoding are provided. A method includes receiving a bitstream including at least one coded picture, inferring a value of a first identifier of a video parameter set, based on the first identifier of the video parameter set not being in the bitstream, and decoding the at least one coded picture based on the inferring.

Abstract: Simulating a 3D audio environment, including receiving a visual representation of an object at a location in a scene, wherein the location represents a point in 3D space, receiving a sound element, and binding the sound element to the visual representation of the object such that a characteristic of the sound element is dynamically modified coincident with a change in location in the scene of the visual representation of the object in 3D space.

Abstract: A picture coding method of the present invention codes a picture signal and a ratio of a number of luminance pixels and a number of chrominance pixels for the picture signal, and then one coding method out of at least two coding methods is selected depending on the ratio. Next, data related to a picture size is coded in accordance with the selected coding method. The data related to the picture size indicates a size of the picture corresponding to the picture signal or an output area, which is a pixel area to be outputted in decoding in a whole pixel area coded in the picture signal coding.

Abstract: An apparatus generates an image signal in which pixels are encoded in N-bit words which encode at least a luma per pixel. A receiver (201) obtains high dynamic range pixel values in accordance with a first color representation in M-bitwords. A first generator (203) includes the high dynamic range pixel values in the image signal in the N-bit words according to a second color representation. A second generator (205) includes in the image signal an indicator that high dynamic range pixel values are encoded. In some examples, the high dynamic range pixel values may be provided in a segment that can alternatively contain high or low dynamic range pixel values, and the indicator may indicate which type of data is included. The approach may e.g. facilitate introduction of high dynamic range capability into e.g. HDMI systems.