Abstract: A method, computer program, and computer system is provided for splitting viewport bitstreams. A first coded video bitstream is at least partially encoded using a first Group-of-Pictures (GOP) structure at a first resolution. A second coded video bitstream structured into a plurality of tiles is encoded using a second GOP structure at a second resolution, whereby the second GOP structure includes fewer coded pictures than the first GOP structure. A streaming bitstream for decoding or rendering is created using the first coded video bitstream and the second coded bitstream.

Abstract: Methods and apparatus provide cloud-based video encoding that generates encoded video data by one or more encoders in a cloud platform for a plurality of cloud encoding sessions. The methods and apparatus generate operational improvement tradeoff data in response to operational encoding metrics associated with the one or more encoders and change operational characteristics of the one or more encoders for at least one of the cloud encoding sessions based on the operational improvement tradeoff data.

Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.

Abstract: A method of encoding image data, including: frequency-transforming input image data to generate an array of frequency-transformed input image coefficients by a matrix-multiplication process, according to a maximum dynamic range of the transformed data and using transform matrices having a data precision; and selecting the maximum dynamic range and/or the data precision of the transform matrices according to the bit depth of the input image data.

Abstract: A method and apparatus for transmitting adaptive video in real time using a content-aware neural network are disclosed. At least one embodiment provides a method performed by a server for transmitting an adaptive video in real time by using content-aware deep neural networks (DNNs), including downloading a video, encoding a downloaded video for each of at least one resolution, dividing an encoded video into video chunks of a predetermined size, training the content-aware DNNs by using encoded video, generating a configuration or manifest file containing information on trained content-aware DNNs and information on the encoded video, and transmitting the configuration file upon a request of a client.

Abstract: A video encoding method comprises encoding a series of images of original video data into an encoded video stream comprising key frames and delta frames, wherein the delta frames are organized in a hierarchical prediction pattern comprising a plurality of temporal layers. The video encoding method further comprises adding to the encoded video stream a hidden delta frame for at least some of the key frames. Each hidden delta frame corresponds to a key frame, is based on same original video data as the corresponding key frame and is referring to a previous key frame in the encoded video stream. Also, a method of reducing a file size of the video stream encoded according to the video encoding method is disclosed.

Abstract: Prediction information of a current block is decoded. The prediction information indicates an affine merge model, and the current block includes control points. A first candidate control point motion vector (CPMV) for a first control point of the control points is determined based on one of at least two CPMVs of a first neighboring block of the first control point and a translational motion vector of a second neighboring block of the first control point. Affine merge candidates for the current block are derived based on candidate CPMVs for the control points of the current block. The candidate CPMVs of the control points includes the first candidate CPMV. Parameters of the affine merge model are determined based on one of the affine merge candidates that is defined according to the prediction information. At least a sample of the current block is reconstructed according to the affine merge model.

Abstract: Aspects of the disclosure provide methods and apparatuses for use in video coding for machines. In some examples, an apparatus of video coding for machines includes processing circuitry. The processing circuitry determines a first picture quality vs. coding efficiency characteristic for a first coding scheme of video coding for machines (VCM), and a second picture quality vs. coding efficiency characteristic for a second coding scheme of VCM. Then, the processing circuitry determines a Bjøntegaard delta (BD) metric for a comparison of the first coding scheme and the second coding scheme, based on the first picture quality vs. coding efficiency characteristic and the second picture quality vs. coding efficiency characteristic.

Abstract: Techniques for psychovisually optimized dithering for image and video (e.g., frame) encoding are described. According to some embodiments, a computer-implemented method includes receiving a request to encode a video from a first depth of pixel values to a second, different depth of pixel values at a content delivery service, detecting a flat region without texturing and a non-flat region with texturing in a first frame of the video having the first depth of pixel values, dithering pixel values in the non-flat region and flattening pixel values in the flat region, encoding the dithered pixel values and the flattened pixel values of the frame into a first encoded frame having the second, different depth of pixel values by the content delivery service, and transmitting the first encoded frame from the content delivery service to a viewer device.

Abstract: A method, computer program, and computer system is provided for video coding. Video data including one or more frames is received. A static background is estimated for each of the one or more frames based on a temporal average of the one or more frames. Pixels from among the one or more frames are identified as corresponding to the static background. Noise is removed in the static background based on the identified pixels.

Abstract: The disclosed computer-implemented method may include downsampling and encoding one or more video segments into a plurality of encoded segments with an analysis encoder using a plurality of encoding parameter value sets and decoding and upsampling the plurality of encoded segments to a plurality of decoded segments at an original resolution of the one or more video segments. The method may further include determining, based on analyzing the plurality of decoded segments, an analysis encoding parameter value set for the analysis encoder for the one or more video segments and predicting, based on the analysis encoding parameter value set, a target encoding parameter value set for a target encoder for the one or more video segments. The method may also include encoding the one or more video segments with the target encoder using the target encoding parameter value set. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: This application relates to a method and an apparatus for processing encoded data, a computer device, and a storage medium. The method includes: obtaining a to-be-encoded data frame; determining a complexity of the to-be-encoded data frame, the complexity representing at least a spatial texture complexity and a temporal motion intensity; obtaining a real-time encoding bit rate, the real-time encoding bit rate being an encoding bit rate of a previous encoded data frame of the to-be-encoded data frame; and adjusting an encoding parameter according to the real-time encoding bit rate and the complexity of the to-be-encoded data frame. The encoding parameter is adjusted according to the real-time encoding bit rate and the complexity, and different real-time encoding bit rates and complexities may correspond to different encoding parameters. In this way, the encoding parameter is applicable to different scenes, thereby achieving high adaptability.

Abstract: A method for sharing the motion estimation and mode decision results and decisions of one codec with another codec is disclosed. A video is received to be transcoded into a plurality of different output encodings of a plurality of different codecs. Each codec has a different video encoding format. A shared motion estimation and a shared mode decision processing of the video are performed. One or more results of the shared mode decision processing shared across the plurality of different codecs are used to encode the video into the plurality of different output encodings of the plurality of different codecs.

Abstract: An image signal decoding method according to an embodiment of the present disclosure comprises the steps of: partitioning the current picture into a plurality of tiles; decoding partition information indicating a slice type, the partition information indicating whether a rectangular slice is to be applied; determining the number of slices in the current picture; and defining the slices using the tiles.

Abstract: A temporal domain rate distortion optimization based on video content characteristic and QP-? correction provides the temporal domain rate distortion optimization based on the video content characteristic and the QP-? correction for a new generation encoder AV1, wherein according to a previous temporal domain dependency relationship under an HEVC-RA coding structure, a feature of the new generation encoder AV1 and a video sequence feature, an aggregation distortion of a current coding unit and an affected future coding unit is estimated and ta propagation factor of the current coding unit in a temporal domain distortion propagation model is calculated by constructing a temporal domain distortion propagation chain, wherein a Lagrange multiplier is adjusted through a more accurate propagation factor to realize a temporal domain dependency rate distortion optimization, and a relationship of QP-? is re-corrected and an I frame is adjusted to achieve a better coding effect.

Abstract: Security devices and associated methods have a housing, a camera with a field of view of a monitored area outside the housing, a microphone to sense audio from the monitored area, a speaker to generate sound audible to the monitored area, an illumination source to illuminate the monitored area, a communication module to communicate with a communication network, a motion sensor to detect motion within the monitored area, at least two removable battery casings, each configured via a release button to hold at least one battery within the housing, and a control circuit that, when the motion sensor detects motion, is operable to (a) activate the illumination source, (b) capture video and audio from the camera and the microphone, and (c) send the captured video and audio to a remote server via the communication module and the communication network.

Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.

Abstract: Hyperspectral, fluorescence, and laser mapping imaging with a minimal area image sensor are disclosed. A system includes an emitter for emitting pulses of electromagnetic radiation and an image sensor comprising a pixel array for sensing reflected electromagnetic radiation, wherein the pixel array comprises active pixels and optical black pixels. The system includes a black clamp circuit providing offset control for data generated by the pixel array. The system is such that at least a portion of the pulses of electromagnetic radiation emitted by the emitter comprises one or more of: electromagnetic radiation having a wavelength from about 513 nm to about 545 nm; electromagnetic radiation having a wavelength from about 565 nm to about 585 nm; electromagnetic radiation having a wavelength from about 900 nm to about 1000 nm; an excitation wavelength of electromagnetic radiation that causes a reagent to fluoresce; or a laser mapping pattern.

Abstract: A proxy device may organize a set of local devices as members of a union. The proxy device may create a set of virtual peripheral devices. The set of virtual peripheral devices may represent a set of physical peripheral devices connected to the set of local devices. The proxy device may communicate the set of virtual peripheral devices to a remote device.

Abstract: A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.