877 results about "Entropy encoding" patented technology

The present disclosure provides a variable-bit-rate image compression method and system, an apparatus, a terminal, and a storage medium. The variable-bit-rate image compression method includes: obtaining an initial feature map from a to-be-encoded image; quantizing the initial feature map by a dead-zone quantizer; performing entropy encoding on the quantized feature map and hyper-prior information to obtain a compressed bit-stream; performing entropy decoding on the compressed bit-stream, and recovering quantized hyper-prior information and the quantized feature map; performing inverse quantization on the quantized feature map to obtain a reconstructed feature map; obtaining a reconstructed image from the reconstructed feature map; and adjusting quantization and inverse quantization parameters according to a target bit-rate or target distortion. The present disclosure provides a precise bit-rate control solution, makes the bit-rate of the compressed bit-stream better adapt to the dynamic change of a network bandwidth, and has an extremely high actual application value.

The invention relates to the technical field of computer vision and image recognition, in particular to an image recognition method based on edge computing, which comprises the following steps: dynamically capturing an original image through a plurality of edge nodes, rejecting redundant regions through a multi-modal perception triggering mechanism, and establishing a cooperative processing group. Illumination equalization, noise filtering and resolution self-adaptive compression tasks are distributed according to dynamic role election, a standardized preprocessed image is generated, a lightweight convolutional neural network is operated in parallel to extract a dual-channel feature vector, and after entropy coding lossless compression and equipment identity tag and time sequence stamp attachment, the dual-channel feature vector is transmitted to a cloud end by adopting a lightweight encryption protocol. The cloud end analyzes the data packet, reconstructs a feature topological graph based on space-time relevance, loads a depth residual error recognition model to execute feature fusion and classification decision, feeds back and updates the weight of an edge node model, solves the problems of low collaborative efficiency and feature distortion, and improves the efficiency and precision of image recognition.

A method for encoding an image includes determining an intra prediction mode of a current block; generating a prediction block of the current block according to the intra prediction mode; generating a residual block by calculating a difference between the current block and the prediction block; transforming the residual block to generate a transform block; quantizing the transform block to generate a quantized block; and entropy-coding coefficients of the quantized block, wherein the generating the prediction block of the current block according to the intra prediction mode includes: generating reference pixels on an unavailable position if there exist unavailable reference pixels of the current block; determining whether reference pixels of the current block are filtered or not based on the intra prediction mode and a block size of the current block; filtering the reference pixels of the current block using a filter if it is determined that the reference pixels of the current block are filtered, wherein the reference pixels are adaptively filtered based on the block size of the current block, wherein the filter is not applied if it is determined that the size of the current block is smaller than a first size, wherein if a number of intra prediction modes to which the filter is applied is increased, it is determined that the size of the current block is larger than the first size and smaller than a second size, and wherein the reference pixels of the current block are not filtered in a horizontal mode because the image is correlated horizontally.

A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of: (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image.

The invention discloses an extreme compressed video coding method based on an intelligent reference frame, comprising the following steps: S1, acquiring an original video stream, dividing the original video stream into frame groups according to a time sequence, each group comprising a current frame and a candidate reference frame; s2, carrying out region positioning on the candidate reference frame, extracting motion, edge and background regions, and generating a mapping graph; s3, calculating a quality score based on the mapping graph according to a motion vector, gradient change and a region overlapping rate; s4, selecting three frames with highest scores to form a reference set, and establishing an index structure; s5, predicting the current frame by using the reference set to generate a predicted frame and a residual error; s6, multi-path coding cost is calculated, and a path with the minimum cost is selected; and S7, entropy coding is carried out on the reference index, the motion vector, the residual error and the control parameter, a code stream is output, and calling information is recorded. According to the method, the compression ratio and prediction precision of video coding are improved, the image quality is maintained while the code rate is reduced, and the method is suitable for efficient transmission and storage of high-resolution videos.

Innovations in systems, methods, and software for features of a neural image or video codec are described herein. For example, a neural video encoder can receive a current video frame, encode the current video frame to produce encoded data, and output the encoded data as part of a bitstream. As part of the encoding, the encoder can determine a current latent representation for the current video frame, and encode the current latent representation using an entropy model network that includes one or more convolutional layers. As part of the encoding the current latent representation, the encoder can estimate statistical characteristics of a quantized version of the current latent representation based at least in part on a previous latent representation for a previous video frame, and entropy code the quantized version of the current latent representation based at least in part on the estimated statistical characteristics.

The invention relates to the technical field of video coding and decoding, and discloses a multi-mode large model-based generative video coding and decoding, which comprises a key frame selection module for determining a key frame by analyzing the semantic and motion characteristics of a video frame; the multi-modal semantic description generation module is used for generating semantic description according to the key frame and the video clip; the key frame compression module is used for realizing efficient compression through latent variable modeling and entropy coding; the key frame reconstruction module reconstructs a key frame by using a conditional diffusion model in combination with the compressed data and the semantic description information; and the video generation module generates a non-key frame by using the semantic description and the key frame, and reconstructs a complete video. Through key frame screening combining semantic and motion information, key frame compression and reconstruction based on a conditional latent variable diffusion model, and frame supplementation and frame insertion generation based on semantic description, efficient compression and high-quality video reconstruction can be realized under a low code rate, and the video storage efficiency and the visual quality are effectively improved.

A video encoder is configured to entropy encode an absolute value of a quantization level of a current transform coefficient at position (xC, yC), wherein the absolute value is encoded using context adaptive binary arithmetic encoding of bins of a first binarization. The video coder is further configured, for the current transform coefficient, to encode a bin of the first binarization by using a context which is determined based on a sum of minimum absolute values of transform coefficient quantization levels, based on encoded bins of the first binarization, at one or more transform coefficient positions among (xC+1, yC), (xC+2, yC), (xC+1, yC+1), (xC, yC+1), and (xC, yC+2).

The invention belongs to the field of image / video compression, and discloses an intelligent image compression encoder based on a conditional reversible neural network, which comprises an image enhancement module, a reversible multi-frequency fusion network RMFFN and an entropy model, and is characterized in that the image enhancement module comprises a multi-expansion channel refiner module MDCR and an expansion residual attention module RDAM; the image enhancement module optimizes input features and constructs a conditional reversible neural network by using a flow model, namely, multi-stage nonlinear mapping is realized by stacking four reversible multi-frequency fusion networks; the super-prior codec of the entropy model extracts hidden variable features by stacking multi-scale residual attention blocks, and introduces a discrete Gaussian mixture likelihood model in an entropy coding stage. According to the method, high-fidelity reconstruction is still kept at a low bit rate, and the technical problems of bit rate-distortion balance, high-frequency detail retention and calculation efficiency of a traditional method are solved.

The invention discloses a volume video intelligent coding method, and the method comprises the steps: a feature enhancement module based on view guidance is used for carrying out the feature enhancement of self-adaptive learning anchor features; the progressive entropy coding module based on context guidance is used for performing efficient compression coding on the enhanced anchor point features; the Gaussian attribute feature decoder is used for obtaining each neural Gaussian attribute; and through a neural Gaussian sputtering rendering technology, the neural Gaussian is mapped to a target visual angle, and a high-quality reconstructed viewpoint image is generated. According to the method, the scene information of each view angle is fused into the feature learning process, and the Gaussian attribute progressive coding strategy is constructed, so that the compression efficiency of the volume video is improved.

There is provide an image encoding method including transforming an image block into a first latent representation based on an invertible neural network, transforming the first latent representation into a second latent representation based on a non-invertible neural network, estimating a probability distribution of the first latent representation, and performing entropy encoding on the first latent representation based on the probability distribution by using an entropy encoder.

The invention provides an AI large model source network load storage optimization scheduling method and system, and relates to the technical field of intelligent scheduling, and the method comprises the steps: receiving power system source end power generation, power grid transmission, user load and energy storage equipment data, and carrying out the time label alignment and preprocessing to obtain a system feature data set; determining a current operation scene by using a multi-dimensional scene identifier of energy flow decomposition, and calling an expert model combination to generate an initial scheduling parameter; inputting the parameters into a pre-trained large language model, and generating an optimized scheduling parameter set through probability causal reasoning of variational entropy coding; constructing a differential Monte Carlo continuous sampling flow, adjusting the sampling probability density by adopting a neural optimal transmission theory, and screening parameter subsets meeting risk constraints; and according to the market price signal and the operation constraint, determining an optimal scheduling parameter to execute coordinated scheduling, and feeding back an execution result to the model to perform online iterative optimization. According to the invention, intelligent coordinated dispatching of the power system is realized, and the safety and economy of system operation are improved.

The invention relates to the technical field of voice processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a voice signal compression method, device, equipment and medium, which comprises the following steps: executing Fourier transform on an initial voice signal to extract an amplitude spectrum and a phase spectrum, respectively processing the amplitude spectrum and the phase spectrum to generate features, and splicing the features to obtain a compressed voice signal; the method comprises the following steps: carrying out quantization by adopting a residual vectorization mode to generate a compressed feature vector, executing entropy coding to obtain a compressed code stream, recovering the compressed feature vector at a decoding side, reconstructing a spliced feature through residual reverse quantization, enhancing feature expression through up-sampling operation, and restoring a voice signal through inverse Fourier transform. According to the method, a dual-path processing structure of amplitude features and phase features is constructed, feature compression is realized in combination with residual vectorization and entropy coding, inverse quantization and up-sampling enhancement are executed in a decoding stage, a spectrum energy structure and phase continuity are effectively reserved, and reconstruction precision and fidelity of voice signals are improved under the condition of low bit rate.

The invention provides a sparse representation-based low-bit-rate video coding method, which comprises the following steps of: after a coding end acquires an input video, carrying out frame segmentation sampling on the input video to obtain a video frame sequence, and carrying out block segmentation on elements in the video frame sequence to obtain an image block sequence; processing elements in the image block sequence based on a dictionary learning algorithm and a sparse representation algorithm of gradient sparsity to obtain a sparse representation coefficient; sequentially performing quantization processing and entropy coding processing on the sparse representation system to obtain a compressed bit stream, and storing and transmitting the compressed bit stream; obtaining a compressed bit stream, and sequentially performing entropy decoding processing and inverse quantization processing on the bit stream to obtain an original sparse representation coefficient; processing the original sparse representation coefficient based on a dictionary learning algorithm and a sparse decoding algorithm of gradient sparsity to obtain a reconstructed image block; merging the plurality of reconstructed image blocks to obtain a reconstructed video frame; and carrying out frame combination on the plurality of reconstructed video frames to obtain a reconstructed input video.

A neural network-based image processing method and apparatus according to an embodiment of the present invention may: acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers; acquire a symbol tensor by performing quantization on the acquired feature tensor; and generate a bitstream by performing entropy encoding on the basis of the symbol tensor.

A device is configured to decode a mesh from a bitstream that includes the encoded mesh data, wherein, as part of decoding the mesh, one or more processors of the device are configured to determine, based on encoded mesh data, a base mesh that includes a set of vertices; apply the entropy decoding to first, second, and third entropy-encoded data comprises using a shared non-bypass context for entropy decoding at least one bin of each of the first truncated unary (TU) data, the second TU data, and the third TU data, where the first, second, and third TU data are included in binarized representations of syntax elements representing first and second residual values of components of normal vectors of vertices and a second residual value of a component of a normal vector of a vertex.

A method for encoding and decoding, an encoder and decoder for a point cloud. The method for encoding a point cloud to generate a bitstream of compressed point cloud data, in which the point cloud's geometry is represented by an octree-based structure with a plurality of nodes having parent-child relationships by recursively splitting a volumetric space containing the point cloud into sub-volumes each associated with a node of the octree-based structure, includes: determining an occupancy pattern for a parent node based on the occupancy of its child nodes; determining a planar context information for at least one of the child nodes; and entropy encoding / decoding the occupancy pattern parent node based on the determined planar context information to produce encoded / decoded data for the bitstream.

Decoding a current block includes receiving a compressed bitstream. A transform block of transform coefficients is decoded from the compressed bitstream. The transform coefficients are in a transform domain. The transform block is input to a machine-learning model to obtain a residual block that is in a pixel domain. The residual block is used to reconstruct the current block. Encoding a current block includes receiving a current residual block. The current residual block and a specified rate-distortion parameter are input to a machine-learning model to obtain a quantized transform block. The quantized transform block is entropy encoded into a compressed bitstream.

The invention relates to the technical field of data processing, in particular to a cloud database data compression method based on an adaptive quantization algorithm. The method comprises the following steps of: 1, regarding to-be-compressed original data in a cloud database as a matrix, dividing the data into a plurality of non-overlapped data blocks according to predefined statistical characteristics, and calculating a mean value and a variance of each data block; 2, defining the complexity of each data block, and calculating the self-adaptive quantization step length of each data block according to the mean value and variance of each data block; step 3, performing non-uniform adaptive quantization on each data item in each data block to obtain a quantized value; and 4, establishing a probability model for a quantization result of each data block, calculating a coding length, obtaining a compression ratio, and carrying out entropy coding. The quantization step size of the data block is dynamically adjusted to be matched with the local characteristic of the data, so that the quantization error is reduced, and the data recovery precision is improved.

In one implementation, we propose a scalable framework where a base layer uses NN-based methods to compress the content for computer vision machine tasks and enhancement layer(s) use traditional predictive coding for human viewing. Typically, the based layer performs NN-based analysis to generate a latent tensor, which is entropy coded to produce the base layer bitstream. By performing synthesis on the latent tensor, an inter-layer predictor can be obtained for the enhancement layer(s). Since many machine tasks are not required to be performed for each frame, the base layer may skip analysis for some frames. The synthesis may be performed at the base layer or the enhancement layer(s). In one example, the base layer compresses features optimized for a machine task and the enhancement layer(s) rely on predictive coding. In another example, the enhancement layer(s) can use traditional scalable video compression methods.

The invention discloses a dual-path three-dimensional point cloud compression reconstruction method fusing multi-scale geometric features. The method comprises the following steps: extracting representative skeleton anchor points from original point clouds by adopting farthest point sampling; predicting an octree node occupancy state by using an anchor encoder, and performing entropy coding to generate a skeleton bit stream; a skeleton condition feature encoder is introduced, probability distribution of local features is predicted by using skeleton context priori, cross-path context association is constructed, and a feature bit stream is generated; in the decoding stage, the sparse skeleton point set is restored from the skeleton bit stream, local features are recovered from the feature bit stream in combination with the skeleton structure context, fine-grained reconstruction is carried out on the point cloud through a geometric fusion point cloud up-sampling module, and finally the high-fidelity point cloud is obtained. According to the invention, the point cloud compression effect and reconstruction quality can be improved. The method can be widely applied to the point cloud field.

The invention provides a coding and decoding method and electronic equipment. The method comprises the following steps: performing motion estimation on a current frame to obtain a first optical flow; obtaining first optical flow super-prior information based on the feature information of the first optical flow and the prior information of the first optical flow; encoding the first optical flow hyper-prior information to obtain a first code stream; probability estimation is carried out based on the second optical flow hyper-prior information and the prior information of the first optical flow, and optical flow probability distribution is obtained; entropy coding is carried out on the feature information of the first optical flow based on the optical flow probability distribution to obtain a second code stream; performing inter-frame prediction on the current frame to obtain prediction information; determining residual information based on the prediction information and the original image; and encoding the residual information to obtain a third code stream. Compared with the prior art that the determined first optical flow hyper-prior information is used for determining the optical flow probability distribution of all the pixel points in the current frame, the first optical flow hyper-prior information is used for determining the optical flow probability distribution of part of the pixel points in the current frame, and the code rate overhead can be reduced.

Provided is a method of decoding coefficients included in image data, the method including determining a Rice parameter for a current coefficient, based on a base level of the current coefficient; parsing coefficient level information indicating a size of the current coefficient from a bitstream by using the determined Rice parameter; and identifying the size of the current coefficient by de-binarizing the coefficient level information by using the determined Rice parameter.

The invention provides a voice reconstruction method and system based on entropy coding residual quantization and frequency spectrum restoration, and relates to the technical field of artificial intelligence voice signal processing, and the method comprises the steps: obtaining an original voice waveform, inputting the voice waveform into a neural voice coding and decoding model, firstly entering a coder to map the input voice waveform into acoustic potential representation, and then entering a frequency spectrum restoration model; performing residual quantization on the acoustic potential characterization layer by layer through a residual vector quantization module, introducing a gating-based dynamic layer number selection mechanism and entropy regularization constraint, enabling bits to be adaptively distributed among different voice segments, reconstructing reconstructed acoustic features of the potential characterization, inputting the reconstructed acoustic features into a decoder, restoring the reconstructed acoustic features into a time domain waveform, and outputting the time domain waveform. And mapping to a logarithmic magnitude spectrum domain through a spectrum repairing module, predicting a residual error in the logarithmic magnitude spectrum domain and performing confidence gating fusion to obtain a complex spectrum, and outputting after time domain synthesis to obtain reconstructed speech. According to the invention, high fidelity, intelligibility and transmission reliability of the voice can be considered at an extremely low bit rate.

The present application provides a data encoding and decoding method and related devices, and relates to the field of data processing. In the encoding method, side information feature extraction is performed on a first feature map of current data, and then quantization processing is performed to obtain a first quantized feature map. Entropy encoding is performed based on the first quantized feature map to obtain a first bitstream of current data. A scaling coefficient is obtained based on the first quantized feature map, and scaling processing is performed on a second feature map based on the scaling coefficient, and then quantization processing is performed to obtain a second quantized feature map. Scaling processing is performed on a first probability distribution parameter based on the scaling coefficient to obtain a second probability distribution parameter, and then entropy encoding is performed on the second quantized feature map based on the second probability distribution parameter to obtain a second bitstream of current data. The second feature map and the first probability distribution parameter are scaled by using the same scaling coefficient so that the degree of coincidence between the second probability distribution parameter and the second quantized feature map is higher, thereby improving the encoding accuracy of the second quantized feature map.

The invention discloses a novel digital hybrid coding method based on a large model. The method comprises the following steps: S1, preprocessing to-be-coded data; s2, performing feature coding on the preprocessed data by adopting a diffusion model driven feature learning method; s3, performing neural network coding on the feature coding data, and dynamically adjusting the coding bit number based on a variable bit rate quantization method; s4, performing adaptive entropy coding on the neural network coding data, and performing probability density transformation based on a normalized flow entropy coding method; s5, discrete transform coding is carried out on entropy coding data, and hierarchical quantization is carried out on different frequency components by adopting a hierarchical sub-block quantization method; and S6, based on the code length distribution and entropy coding parameters of the A3C optimization transformation coding data, extracting a lightweight coding model from the diffusion model by using a knowledge distillation method, and generating final optimization coding data. Through the hybrid coding and dynamic optimization strategy, the data compression efficiency and the coding quality are remarkably improved.

The embodiment of the invention provides a Gaussian point cloud rendering method and device, equipment and a storage medium, and relates to the technical field of computer vision. The method comprises the following steps: acquiring pixel points of foreground targets in two corresponding key frames, generating a double-view-angle Gaussian point cloud based on the pixel points, quantifying double-view-angle Gaussian parameters of the double-view-angle Gaussian point cloud based on different rate-distortion coefficients to obtain quantized Gaussian parameters corresponding to each rate-distortion coefficient, and obtaining the target foreground target in the two key frames according to the quantized Gaussian parameters of the double-view-angle Gaussian point cloud and the quantized Gaussian parameters of the double-view-angle Gaussian point cloud. At least entropy coding is carried out on the quantized Gaussian parameter to obtain a coded Gaussian parameter; and determining a target rate-distortion coefficient according to the definition requirement, selecting a coding Gaussian parameter corresponding to the target rate-distortion coefficient as a target coding Gaussian parameter, and sending at least one target coding Gaussian parameter corresponding to each dual-view sequence to a decoding end. The frame extraction operation is performed on the video frame, so that the data volume can be reduced. Secondly, quantitative Gaussian parameters corresponding to different definitions are obtained according to different rate distortion coefficients, and balance of data transmission and rendering quality is achieved.

The invention relates to probability estimation in multi-symbol entropy coding. Entropy coding, such as multi-symbol arithmetic coding, is used for video compression to encode data into a compressed bitstream for transmission. Some entropy coding techniques are adaptive, which means that the probability distribution is updated instantly based on data. Accuracy of cumulative probability estimation in adaptive multi-symbol arithmetic coding may affect coding efficiency. To solve this problem, a mixture of two or more adaptive cumulative probability estimates calculated using two or more adaptation parameters may be used in place of a single cumulative probability estimate. The two or more adaptation parameters may be unique to the context model. The divergence in the adaptive cumulative probability estimation may represent a sudden change in the probability of the symbol. The divergence may trigger a reset of one or more adaptive cumulative probability estimates.

The invention discloses a machine vision-oriented three-dimensional image coding method, which comprises the following steps of: performing feature extraction on input left and right views by using a three-dimensional image feature extraction module to obtain three-dimensional image multi-scale features containing 3D scene information; a stereo image multi-scale feature coding module is used for coding the stereo image multi-scale features to obtain compact left and right viewpoint potential representations, and stereo entropy coding is carried out on the left and right viewpoint potential representations to obtain code streams for transmission; performing stereo entropy decoding on the transmitted code stream to obtain decoded left and right viewpoint potential representations, and decoding the left and right viewpoint potential representations at a decoding end by using a stereo image multi-scale feature decoding module to obtain reconstructed stereo image multi-scale features; and performing visual analysis on the reconstructed stereo image multi-scale features by using a 3D visual analysis module to obtain a 3D target detection result. According to the invention, the 3D visual task performance and the stereo image compression efficiency are effectively improved.

The invention relates to the technical field of machine learning, and discloses a feature disassembly and compression method and device, equipment and a storage medium, and the method comprises the steps: obtaining an initial feature of to-be-predicted image data, determining an expert activation weight corresponding to a downstream prediction task based on a hybrid expert network, the initial features are processed through a plurality of expert networks in the hybrid expert network to generate disassembled features, the plurality of expert networks are networks constrained through a low-rank matrix, the disassembled features are quantized to generate quantized features, entropy coding is carried out on the quantized features through a hyper-prior network, and compressed features are obtained. According to the method, the expert activation weight is dynamically adjusted along with task requirements, different task scenes are adapted, initial features are disassembled based on a plurality of expert networks, task irrelevant information is explicitly stripped, task key features are reserved, redundant data volume is reduced, quantized coding is performed on disassembled feature input, code stream self-adaption is realized, and bandwidth occupation is reduced.