Abstract: The various implementations described herein include methods and systems for coding video. In one aspect, a video decoding method includes receiving a multi-view video bitstream comprising a plurality of pictures. The plurality of pictures includes a first picture corresponding to a first view and a second picture corresponding to a second view. The method includes determining whether reference picture information is shared for the first picture and the second picture. The method includes, when the reference picture information is shared, decoding the first picture and the second picture using the reference picture information.

Abstract: A transmission device of point cloud data, a method performed by the transmission device, a reception device and a method performed by the reception device are provided. A method performed by a reception device of point cloud data comprises acquiring temporal scalability information of a point cloud in a three-dimensional space based on a G-PCC file and reconstructing the three-dimensional point cloud based on the temporal scalability information. The temporal scalability information may comprise a first syntax element and a second syntax element for the three-dimensional point cloud, the first syntax element may indicate the number of temporal levels in a track, the second syntax element may indicate whether the three-dimensional point cloud is carried in multiple temporal level tracks, and the second syntax element may be determined based on a value of the first syntax element.

Abstract: An intra-prediction method includes: determining, by an intra-prediction apparatus, a directional intra-prediction mode for a rectangular video coding block from an extended set of directional intra-prediction modes, wherein the extended set of directional intra-prediction modes includes extended directional intra-prediction modes and conventional directional intra-prediction modes and determining, by the intra-prediction apparatus, a plurality of available reference samples based on a direction of the directional intra-prediction mode. The method further includes: intra-predicting, by the intra-prediction apparatus, pixel values of pixels of the rectangular video coding block based on the plurality of available reference samples.

Abstract: A video encoder and decoder system employing a compression-decision generative adversarial model (“CDGAM”) has an encoder with a compression network and a decoder with a task network. The compression network is a generator portion of a pretrained CDGAM and the task network is a discriminator portion of the pretrained CDGAM. The compression network and task network are trained using common image data wherein the compression network is trained to a generate minimal compressed representation that results in a substantially similar loss as the original image at the discriminator.

Abstract: An interactive warning pad provides static tactile feedback with a raised set of knobs over the interactive warning pad surface to notify users of a potential hazard. The interactive warning pad also provides enhanced or different sensory feedback to identify a specify type of hazard that the interactive warning pad is intended to protect against and different states associated with the hazard. The interactive warning paid includes a covering with the raised set of knobs. The knobs have translucent tops and lighting elements are positioned under the raised knobs. A controller controls different illuminations of the lighting elements in response to different monitored states of the hazard with the different illuminations identifying the hazard and the hazard state. The interactive warning pad may also include vibration motors, a speaker, and/or a wireless transceiver for additional sensory feedback that identifies the specific type of hazard and hazard state.

Abstract: Providing backward compatibility in terms of a media bitstream and a media player conforming to different versions of a media bitstream syntax specification. In one embodiment, a bitstream is made backward compatible by including in the bitstream a first entry for a feature available in the media bitstream and second entry for an updated feature available in the media bitstream, where the first entry is understood both by a media player supporting a first version of a syntax specification and a media player supporting an updated version of the syntax specification, and the second entry is understood by the media player supporting the updated version of the syntax specification, but is not understood by the media player supporting the first version of the syntax specification.

Abstract: A head-tracking multiview display includes a multibeam backlight that provides a plurality of light beams having different principal angular directions corresponding to different view directions of a multiview image. A processor receives a plurality of provisional views of the multiview image. The provisional views correspond to the different view directions. The processor receives information about a tracked position of a user. The processor shifts the provisional views with respect to the view directions to form a plurality of shifted views that correspond to the different view directions. The shifted views are shifted by a shift value that varies as a function of the tracked position of the user and varies over a field of view of the multiview image. A light valve array modulates the plurality of light beams to provide the plurality of shifted views of the multiview image to the view directions as the multiview image.

Abstract: Techniques and devices are described for processing point cloud data. An example device includes one or more memories and one or more processors. The one or more processors are configured to process a syntax element indicative of whether a previous previous frame can be used for inter prediction for one or more points of point cloud data. The previous previous frame includes a reference frame of a previous reference frame. The one or more processors are configured to code the one or more points based on a determination of whether the previous previous frame can be used for inter prediction for the one or more points.

Abstract: Methods and apparatuses for encoding/decoding data content representative of a volumetric video are provided, wherein, the encoding/decoding comprises encoding in/decoding from a bitstream, an indicator specifying whether data content has information representative of at least one set of depth layers, the information representative of a set of depth layers specifying a number of depth layers and a depth value for each of the depth layers for a layer-based representation of the volumetric video. Methods and apparatuses for reconstructing Computer Generated Holograms from a reconstructed layered-based representation of the volumetric video are also provided.

Abstract: The embodiments relate to a method for encoding and decoding, and to apparatuses for the same. The method for encapsulating includes receiving a visual volumetric video-based coding bitstream containing common atlas bitstream and one or more atlas bitstreams; storing the common atlas bitstream and the one of the one or more atlas bitstreams in samples of one track or in an item data of one item in a file; providing a signaling in the file that indicates that the samples of the one track or the item data of the one item contains both common atlas data and atlas data; and writing in the file the signaling and the samples of the one track or the item data of the one item containing both common atlas data and atlas data. The embodiments also relate to a method for decapsulating and apparatuses for implementing the method for encapsulating and decapsulating.

Abstract: There is provided a method of automatically detecting paint anomalies on a vehicle, comprising: operating illumination elements configured for generating illuminations of different types at first different frequency bands and/or at first different polarization angles, positioned for illuminating the vehicle, operating image sensors for capturing the images, wherein the image sensors are of different modalities configured for sensing at second different frequency bands and/or at second different polarization angles configured for capturing images of a vehicle, extracting features from the images, generating a multi-dimensional dataset by aggregating the features, feeding the multi-dimensional dataset into a machine learning model, obtaining from the machine learning model, an indication of a region of the vehicle with a paint anomaly, generating an enhanced image depicting the region of the vehicle with the paint anomaly overlaid with a visual indication of the region with the paint anomaly, and presenting the

Abstract: Methods, apparatuses, and systems for haptic signal processing are provided and include receiving a media stream comprising data in a haptics interchange format, obtaining, from the data in the haptics interchange format of the media stream, a syntax of an ISOBMFF haptic sample, wherein the syntax indicates a variable value of a data_packet_type of the media stream, and decoding the media stream based on the syntax.

Abstract: A method and an apparatus for converting film grain metadata are provided. In an embodiment, a first film grain metadata is obtained, the first film grain metadata complying with a first film grain syntax and being representative of a first film grain model. At least one part of the first film grain metadata is converted to at least one part of a second film grain metadata, the second film grain metadata complying with a second film grain syntax and being representative of a second film grain model, wherein the second film grain syntax is different from the first film grain syntax, or the second film grain model is different from the first film grain model, or both the second film grain syntax and the second film grain model are different from the first film grain syntax and the first film grain model.

Abstract: An apparatus configured to encode video data is configured to receive a first picture captured at a first time and a first location, receive a second picture captured at a second time and a second location, wherein the second time is different from the first time, and wherein the second location is different than the first location, and encode a current block of the second picture, relative to the first picture, using affine motion prediction with a single parameter search, wherein the single parameter search is performed along an epipolar curve, and wherein the single parameter search is used to determine parameters of an affine motion model.

Abstract: The present disclosure provides a decoding method and apparatus, a coding method and apparatus, and a device. The method comprises: on the basis of on a first code stream corresponding to a current block, acquiring a target probability distribution model corresponding to a first scaling factor; on the basis of the target probability distribution model corresponding to the first scaling factor, decoding a second code stream corresponding to the current block, to obtain a corrected residual feature corresponding to the current block; and, on the basis of the corrected residual feature, determining a reconstructed image block corresponding to the current block. The present disclosure improves the coding performance and the decoding performance.

Abstract: A method for extracting urban flood inundation extent based on remote sensing images includes: acquiring and preprocessing a Fengyun-4 satellite remote sensing image to obtain a preprocessed remote sensing image, and dividing the preprocessed remote sensing image into a thin cloud area and a thick cloud area; removing thin clouds and thick clouds in the preprocessed remote sensing image; extracting a first water body area from the cloud-removed remote sensing image to obtain a first urban inundation extent; acquiring a radar image at a same region and a same time as the remote sensing image, and extracting a second water body area from the radar image to obtain a second urban inundation extent; and training a super-resolution convolutional neural network according to the first urban inundation extent and the second urban inundation extent, and using a trained super-resolution convolutional neural network to obtain a reconstructed higher-resolution urban flood inundation extent.

Abstract: An example method of video coding includes receiving a video bitstream for a plurality of encoded pictures. The method also includes deriving, using frame interpolation, a reconstruction picture for an encoded picture of the plurality of encoded pictures. The method further includes determining, based on a signaled indicator in the video bitstream, whether one or more quantization parameters for the encoded picture are signaled in the video bitstream. When the signaled indicator indicates that the one or more quantization parameters are signaled in the video bitstream, the one or more quantization parameters are parsed from the video bitstream. When the signaled indicator indicates that the one or more quantization parameters are not signaled in the video bitstream, the one or more quantization parameters are derived at the decoder.

Abstract: An indication of a start point of a user interface gesture on an image of a displayed stream from a camera is received. A visual overlay representing a direction and a magnitude of the user interface gesture is provided as the user interface gesture is updated while maintaining current pan and tilt settings of the displayed stream. An indication of an end point of the user interface gesture is received. Amplitudes of changes for the current pan and tilt settings are determined based on the user interface gesture. Pan and tilt control instructions are generated based on the determined amplitude of changes. The generated pan and tilt control instructions are provided to a camera controller for physically modifying pan and tilt of the camera.

Abstract: A system and method for video and feature coding of neural-network structures used for multi-task machine learning includes an encoder, decoder and a decoder-compliant bitstream. A task-specific video decoder includes a first decoder receiving a bitstream having at least one feature and a description of a neural network backbone used to generate the bitstream, and a task-specific neural network head. The neural network head recreates the neural network backbone from the description, receives a feature from the bitstream a generates a task-specific output.

Abstract: Examples of video encoding methods and apparatus and video decoding methods and apparatus are described. An example method of video processing includes performing a conversion between a video including multiple layers and a bitstream of the video according to a rule, wherein the rule specifies that, in a first process of sub-bitstream extraction to output a first output sub-bitstream, the first output sub-bitstream is extracted without removing network abstraction layer (NAL) units of a particular type and having a particular NAL unit header identifier value, and wherein the particular type includes an access unit delimiter (AUD) NAL unit.