Provided are a device and operating method thereof for obtaining compression ratio information for recognizing a target object in an image using a deep neural network model, and compressing an image using the compression ratio information and encoding the compressed image. According to an embodiment of the present disclosure, there is provided a device that receives an image via at least one camera or a communication interface, obtains a feature map for detecting a target object in the received image, outputs a compression ratio for correctly recognizing the target object in the image by inputting the image and the feature map to a deep neural network model composed of pre-trained model parameters, and generates a bitstream by compressing the image using the output compression ratio and encoding the compressed image.

Techniques are disclosed for the creation of multi-codec encoding profiles (or encoding ladders), which define quality and bitrate for each of the streams made available to clients for streaming a video. In particular, optimization techniques may take into account a quality rate function of each of the codecs when determining the encoding ladder. Additional considerations may include a network bandwidth distribution and/or a distribution of client types.

The present invention relates to an image encoding/decoding method and apparatus. The image decoding method according to the present invention may comprise configuring an MPM list based on intra-prediction modes of neighbor blocks of a current block and a number of frequencies of the intra-prediction modes of the neighbor blocks, deriving an intra-prediction mode of the current block based on the MPM list, and performing intra-prediction for the current block based on the intra-prediction mode.

A coding method and an apparatus are provided. XR data of different dimensions or different QoS requirements are distinguished during coding.

Embodiments of a system and method for secure processing of image data are described. Image data included in image files may be encrypted and compressed in a single step using dynamically identified compression/encryption information such as code word tables.

An image decoding method includes obtaining, from a bitstream, first information indicating a motion vector resolution of a current unit among plural motion vector resolutions including a first motion vector resolution and a second motion vector resolution, and obtaining, from the bitstream, second information indicating whether a merge mode is applied to the current unit or not when the first information indicates the first motion vector resolution. The current unit is decoded based on the merge mode when the second information indicates that the merge mode is applied to the current unit. When the first information indicates the second motion vector resolution, the second information is not obtained from the bitstream. A picture is split into one or more largest coding units, and a largest coding unit among the one or more largest coding units is split into one or more coding units including the current unit.

Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry that decodes prediction information for a plurality of first blocks in a current coded picture that is a part of a coded video sequence. The prediction information indicates that the plurality of first blocks is coded in a local illumination compensation (LIC) mode. The processing circuitry selects a neighboring region for each of the plurality of first blocks. The selected neighboring region and the respective first block form a second block. The processing circuitry performs an inter prediction for the plurality of second blocks in parallel. The processing circuitry determines a set of LIC parameters for each of the plurality of first blocks based on the selected neighboring region of the respective first block and reconstructs the plurality of first blocks based on the sets of LIC parameters.

Aspects of the disclosure provide methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information for a current block in a current picture that is a part of a coded video sequence. The prediction information includes an adaptive color transform (ACT) flag indicating whether ACT is enabled for the current block. The processing circuitry determines whether a transform unit (TU) split is performed on the current block based on a maximum transform size that is determined according to whether the ACT flag indicates the ACT is enabled for the current block. The processing circuitry determines a type of the TU split in response to the TU split being determined to be performed on the current block. The processing circuitry performs the TU split on the current block based on the determined type of the TU split.

A method for encoding a multi-view frame in a video encoder is provided that includes computing a depth quality sensitivity measure for a multi-view coding block in the multi-view frame, computing a depth-based perceptual quantization scale for a 2D coding block of the multi-view coding block, wherein the depth-based perceptual quantization scale is based on the depth quality sensitive measure and a base quantization scale for the 2D frame including the 2D coding block, and encoding the 2D coding block using the depth-based perceptual quantization scale.

The disclosure regards cross-component prediction and methods for deriving of a linear model for obtaining a first-component sample for a first-component block from an associated reconstructed second-component sample of a second-component block in the same frame, the method comprising determining the parameters of a linear equation representing a straight line passing through two points, each point being defined by two variables, the first variable corresponding to a second-component sample value, the second variable corresponding to a first-component sample value, based on reconstructed samples of both the first-component and the second-component; and deriving the linear model defined by the straight line parameters; wherein said determining the parameters uses integer arithmetic.