Abstract: A method may include applying a first machine learning model trained to perform an open-set detection by at least identifying, based at least on image data indicative of one or more objects present in at least one environment in which one or more vehicles operate, at least one new class of objects. A dataset including a plurality of classes of objects may be updated to include the at least one new class of objects. In some cases, the dataset may be further updated to include a label associated with the at least one new class of objects. A second machine learning model may be trained, or in some cases updated, based at least on the updated dataset including the at least one new class of objects. Related systems and computer program products are also provided.

Abstract: Different quantization matrices may be transmitted corresponding to different block sizes, color components and prediction modes. To more efficiently signal the coefficients of the quantization matrices, in one implementation, a unified matrix identifier matrixId is used, based on a size identifier (sizeId) that relates to CU size with larger sizes listed first, and a matrix type (matrixTypeId) with luma QMs listed first. For example, the unified identifier is derived as: matrixId=N*sizeId+matrixTypeId, where N is the number of possible type identifiers, e.g., N=6. This single identifier allows referring to any previously transmitted matrix when using prediction (copy), and transmitting larger matrices first avoids interpolation in the prediction process. When a block uses the Intra Block Copy prediction mode, QM identifier may be derived as if the block uses the INTER prediction mode.

Abstract: Systems, methods, and instrumentalities are disclosed for cross-component depth-luma coding. Depth information may be used as information for joint or cross-component coding of texture information (e.g., luma, chroma, or R, G, B colour component information). The depth information may be used to jointly code the corresponding texture information. In examples, a device may determine whether a coding mode, such as a joint depth-color coding mode (JDCC) (e.g., joint depth-luma coding mode (JDLC)) is used for a current block. If JDCC coding mode is used for the block, then the device may decode depth sample(s) in the block and predict the corresponding color sample(s) (e.g., luma sample(s) and/or chroma sample(s)) in the block based on the decoded depth sample(s).

Abstract: A method comprising: executing a streaming session establishment process allowing establishing a streaming session between two peers in a network, wherein the streaming session establishment process comprises receiving (404) information allowing controlling a power consumption of a decoding process applied for decoding a stream representative of a content to be streamed in the streaming session

Abstract: Methods and apparatuses are described for signaling decoding data in a video bitstream, using a syntax element indicating whether the decoding data are explicitly coded in the video bitstream or inferred from previous data of the video bitstream. A bitstream, a computer-readable storage medium, and a computer program product are also described.

Abstract: Decoding and/or encoding video information included in a bitstream can involve a predicted quantization matrix associated with at least a portion of the video information and a syntax element indicating that at least one coefficient of the predicted quantization matrix is to be interpreted as a residual such that the decoding and/or encoding of at least a portion of the video information is based on a combination of the predicted quantization matrix and the residual, where the syntax element is obtained from the bitstream during decoding, or included in the bitstream during encoding.

Abstract: Compression technology comprises deriving chroma quantization parameter (Qpc) based on luma Qp using luma-to-chroma Qp mapping table. Such a table may be shared by the encoder and the decoder. However, in some cases, signaling such a table in the data stream instead of having it fixed by a standard may be advantageous. The syntax used to encode, signal and decode this table has a cost in terms of bitrate. The present principles propose to signaling of a luma-to-chroma mapping table in the data stream according to different embodiments.

Abstract: Systems, methods, and instrumentalities are disclosed for adapting media (e.g., video) processing operations and/or parameters based on one or more viewing conditions in a media environment (e.g., to achieve power saving). Such viewing conditions may include a distance between a display device and a viewer, a viewpoint or viewing direction of the viewer towards the display device, and/or an ambient light level in the media environment. Aspects of the medical processing that may be adapted based on the viewing conditions may be associated with deblocking, sample adaptive offset (SAO) filtering, adaptive loop filtering (ALF), cross component adaptive loop filtering (CCALF), motion compensation, post-inter prediction processing, bi-prediction, residual scaling, luma mapping, chroma residual scaling (LMCS), geometric block partitioning, HDR signal reconstruction, etc.

Abstract: Provided are methods for detecting when a vehicle is encountering an out of operational design domain (ODD) scenario, which can include training a generative adversarial network (GAN) including a generator network and a discriminator network. The generator network may be trained to generate synthesized scenarios. The discriminator network may be trained to distinguish between true scenarios and the synthesized scenarios generated by the generator network. The trained discriminator network may be applied to detect when a vehicle encounters an out of operational design domain (ODD) scenario. Some methods described also include controlling the motion of the vehicle in response to an output of the trained discriminator network indicating that the vehicle is encountering the out of operational design domain (ODD) scenario. Systems and computer program products are also provided.

Abstract: At least a method and an apparatus are presented for efficiently processing film grain while encoding or decoding video. For example, the method comprises estimating film grain parameters for a plurality of image blocks in an image with film grain, wherein the film grain parameters comprise at least one scaling factor. The estimating further comprises obtaining a plurality of film grain blocks, a film grain block being representative of a film grain estimate in an image block; obtaining a plurality of filtered blocks, a filtered block being representative of an image block without film grain; and determining at least one scaling factor for the plurality of images blocks in the image wherein the at least one scaling factor is adapted to statistics based on the plurality of film grain blocks and on the plurality of filtered blocks.

Abstract: A cross-component dependent tool to be used for a chroma block of a picture is enabled responsive to a size of said chroma block and to a size of at least one luma block co-located with the chroma block. Then, the chroma block is decoded responsive to said enablement of said cross-component dependent tool. A encoding and decoding methods are presented as well as encoding and decoding devices.

Abstract: Methods and apparatus for performing intra prediction in an encoder or a decoder for non-square blocks enable a combination of reference samples from a row above the non-square block and a row to the left of the non-square block to be used for the prediction. In one embodiment, a weighted combination of reference samples are used. In another embodiment, the angles of prediction are extended in the longer direction of the non-square block, such that less angles of prediction are used in the shorter direction.

Abstract: Methods and apparatuses for signaling decoding data in a video bitstream, wherein one uses a syntax element indicating whether the decoding data are explicitly coded in the video bitstream or inferred from previous data of the video bitstream. A bitstream, a computer-readable storage medium and a computer program product are also described.

Abstract: A method and apparatus for performing a forward mapping function or its inverse is implemented through information conveyed in a bitstream to perform mapping. The information can be implemented in a uniform or non-uniform lookup table. A decoder can receive the information and derive the inverse function to be used. In one embodiment, a decoder receives information representative of an inverse mapping function and uses the information to implement an inverse mapping lookup table for intra coded picture portions and can derive a forward mapping lookup table to be used with an inverse mapping lookup table for inter coded picture portions.

Abstract: In a video bitstream, Cb and Cr channels are demultiplexed before dequantization instead of after inverse transformation. In this way, regular Cb and Cr quantization control parameters can be used, optionally with minor adjustments when a video block is joint-chroma coded. In one embodiment, some specific quantization control parameters can be specified. In another embodiment, separate Cb and Cr offsets can be specified for joint chroma coded blocks. In another embodiment, quantization control parameters specific to joint chroma coded blocks can be used for both Cb and Cr channels instead of nominal chroma quantization parameters.

Abstract: A lossless coding mode is proposed in a video coding system comprising a plurality of coding tools, some being lossy by design, some of which can be adapted to become lossless or near lossless. To enable a lossless mode in such system, it is proposed to disable the tools that are lossy by design and use only lossless tools, to adapt some tools to enable lossless coding, and adapt some tools to enable near-lossless coding so that a secondary lossless coding may be applied after residual coding. In some embodiments, a type of residual coding is determined by, when an information indicates that a transform skip residual coding is used, obtaining a flag representative of a special mode, and when this flag is true, determine that regular residual coding must be used instead of the transform skip residual coding that should be used.

Abstract: A method and device for reducing power consumption of display devices proposes to reduce the total amount of light emitted in a perceptually indistinguishable manner based on the on the human visual sensitivity at the position of a pixel. The visibility of the processing can be made to remain provably below threshold, whereas other techniques may not be able to provide such proof. This is achieved by determining a minimum detectable modulation or a corresponding just-noticeable difference based on frequency intensity information for a pixel representative of how much there is of a set of frequencies at the pixel and a contrast sensitivity function representative of a model of human vision that predicts which contrasts at which frequencies are visible to the human eye. Pixel values may be reduced based on this minimum detectable modulation or just-noticeable difference.

Abstract: Provided are methods, systems, and computer program products for programmatic detection of objects with an unknown or uncertain semantic class, and generation of a training data set for such objects that can facilitate further development of machine learning models trained to extract semantic information. Embodiments of the present disclosure can detect discrepancies between sensor data corresponding to multiple representations of an environment, and utilize the identified discrepancies to programmatically select a portion of the sensor data for use as a training data set, e.g., for input to a machine learning model.

Abstract: In at least one embodiment, the use of new coding tools result into an improvement of coding efficiency. In an example embodiment, efficient signaling of these coding tools is conveying information representative of the coding tools utilized for the encoding, for example from an encoder device to a receiver device (for example a decoder or a display), so that the appropriate tools are used for the decoding stage. These tools comprise new partitioning modes, new intra-prediction modes, improved flexibility for the sample adaptive offset and a new illumination compensation mode for bi-prediction blocks.

Abstract: Video coding tools can be controlled by including syntax in a video bitstream that makes better use of video decoding resources. An encoder inserts syntax into a video bitstream to enable a decoder to parse the bitstream and easily control which tools combinations are enabled, which combinations are not permitted, and which tools are activated for various components in a multiple component bitstream, leading to potential parallelization of bitstream decoding.