21 results about "Variable bitrate" 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.

This invention discloses a satellite image compression method under extremely low bandwidth conditions. The steps are as follows: collect a static image dataset; establish a variable bitrate image encoding / decoding network; train the encoding / decoding network; embed a generative adversarial network (GAN) at the decoder and retrain it; embed a super-resolution network after the encoder / decoder and retrain it; the user selects a region of interest (ROI), and the selected region is compressed; the decoder restores the bitstream to an image and displays it; the unselected regions are compressed; when bandwidth is sufficient, the unselected regions are transmitted, and the decoder stitches the images together; super-resolution processing is performed. This image transmission method, under extremely low bandwidth constraints, provides a superior subjective reconstruction effect compared to traditional image coding methods such as JPEG and deep learning-based image coding methods in a large number of test images.

The embodiment of the invention provides a code rate control method and device, a data storage method and device, a video processing method and device, a storage medium and a program product. In the method, content feature information and coding feature information can be extracted from a video clip, the content feature information reflects the content complexity of the video clip, and the coding feature information reflects the coding complexity of the video clip; performing code rate prediction according to the content feature information and the coding feature information to obtain a target code rate used for video coding; predicting a target quality factor used for video coding according to the content feature information and the target code rate; and with the target code rate as a code rate constraint condition, according to the target quality factor, carrying out code rate control with the specified visual quality constant as a target on the coding process of the video clip. In one aspect, encoding may be performed based on a variable code rate to save encoding bandwidth; on one hand, each frame of picture of the coding result can accord with the specified visual quality based on the specified visual quality constant target, so that the video quality and the transmission efficiency are balanced.

The present invention discloses a variable bit rate semantic structured image encoding and decoding method and system. By using a rate control mask with the same spatial scale as the input image, variable bit rate coding capability can be introduced for semantic structured image coding, making it more flexible, thereby having higher coding efficiency and higher flexibility when adapting to intelligent analysis tasks in practical applications.

The application provides a video variable code rate coding method and device based on an implicit neural representation model. The method comprises the following steps: step 1, constructing and training an implicit neural representation model; step 2, calculating possible quantization parameter combinations by using the trained implicit neural representation model according to a specified target code rate; step 3, calculating quantization sensitivity for all quantization parameter combinations and selecting a combination with minimum quantization sensitivity for calibration; and step 4, encoding the calibrated model parameters by using an entropy encoder. The application realizes variable code rate coding by adjusting quantization parameters instead of retraining the model, greatly reduces the training cost and improves the coding efficiency.

The present application discloses a point cloud compression method, apparatus and device with a variable bitrate, and a storage medium. The point cloud compression method with a variable bitrate comprises: acquiring a point cloud to be compressed and a required bitrate; determining a scaling factor corresponding to the required bitrate; and on the basis of the point cloud to be compressed, by means of a preset point cloud compression model and a scale linear transformation module of the point cloud compression model, performing point cloud compression at a scale of the corresponding scaling factor to obtain a compressed point cloud meeting the required bitrate, wherein training configuration parameters of the point cloud compression model include scaling factors, the point cloud compression model comprises the scale linear transformation module, and the scale linear transformation module is used for realizing feature scaling of different scales. According to the present application, by means of the scale linear transformation module of the point cloud compression model, the point cloud to be compressed is scaled on the basis of the scaling factor to obtain the compressed point cloud meeting the bitrate required by a user, and only one point cloud compression model needs to be trained, thereby reducing the resource consumption.

The application provides a variable code rate image compression method, system, device, terminal and storage medium, comprising: obtaining an initial feature map of a to-be-encoded image through a first decomposition transform neural network; quantizing the initial feature map through a dead zone quantizer to obtain a quantized feature map; performing entropy coding on the quantized feature map and super-prior information by using an entropy model to obtain a compressed code stream; performing entropy decoding on the compressed code stream, and recovering the quantized super-prior information and the quantized feature map by using the entropy model; performing inverse quantization on the quantized feature map to obtain a reconstructed feature map; obtaining a reconstructed image through a first synthesis transform neural network; and adjusting parameters of quantization and inverse quantization in the encoding process according to a target code rate or a target distortion, so that the code rate of the compressed code stream is close to the target code rate, or the distortion of the reconstructed image is close to the target distortion. The application provides an accurate code rate control scheme, so that the code rate of the compressed code stream is better adapted to dynamic network bandwidth changes, and has extremely strong practical application value.

The invention discloses a man-machine cooperation variable code rate compression system and method based on Swin Transform, and the system comprises a head feature extraction module which is used for extracting the coding features of an original image; the encoder is used for carrying out nonlinear transformation on the encoding features to obtain a first potential representation; the transmission module is used for carrying out quantization and entropy coding on the first potential representation to obtain a compressed bit stream, and restoring the bit stream into a second potential representation through entropy decoding; a decoder extracting reconstructed features from the second potential representation; a variable bit rate hint module that directs generation of a first potential representation or reconstruction feature based on the compression quality level; the tail machine vision task module is used for executing a machine vision analysis task by utilizing the reconstructed features; and the image reconstruction module is used for reconstructing human vision by using the reconstruction feature. The compression quality and the like are embedded into the coding end and the decoding end, variability of multiple compression qualities can be achieved only by training and storing one compression system, and the training and storage cost is reduced.

This invention relates to a neural video compression method and system based on visual saliency, belonging to the field of computer vision technology. Addressing the problems of existing end-to-end neural video compression methods, such as uniform bitrate allocation across regions within a frame and neglect of differences in human visual perception, this invention deeply integrates a lightweight visual saliency detection network with an end-to-end video compression framework. The method includes: using a saliency detection network with MobileNetV2 as its backbone to extract multi-scale features from video frames, generating a saliency probability map, which is then concatenated with the original video frames and input into a variable bitrate conditional video encoding / decoding framework; adaptively allocating the encoding precision of each region based on the saliency probability map, allowing salient regions to receive more bitrate; and employing an adaptive mask prior entropy model for checkerboard-style step-by-step entropy encoding, combined with spatial and channel-dimensional adaptive quantization to improve encoding efficiency. The system includes a saliency detection module, a variable bitrate conditional video encoding / decoding framework module, and an adaptive mask prior entropy model module, which work together to form an end-to-end optimized video compression system. Experimental results show that, at the same bitrate, the present invention can improve human visual image quality (EW-PSNR) by about 2 dB and save about 50% bitrate at the same quality.

An electronic device and method for variable code rate compression of point cloud geometry are provided. An electronic device stores a set of RD operating points and a coding mode associated with the set of RD operating points. An electronic device receives a 3D point cloud geometry and segments the 3D geometry into a set of blocks. After partitioning, the electronic device selects a block and calculates a set of loss values associated with one or more compression indicators. Such loss values correspond to a set of coding modes associated with at least a subset of the set of RD operating points. The electronic device selects a coding mode from the set of coding modes, a loss value of the coding mode in the set of loss values being lower than a loss threshold of the coding mode. Thereafter, the electronic device encodes the block based on the encoding mode.

The application provides a distortion and perceptual code rate adaptive variable code rate depth image compression method, encoder model construction is carried out, including dividing the image to be encoded into image blocks of different granularities, extracting hierarchical features, and obtaining non-repeated hierarchical features by filtering using an image mask; hierarchical vector quantization codebooks are used to quantize the hierarchical features, discrete index representations are generated, and code stream files are encoded; decoder model construction, including decoding the code stream files into discrete index representations, recovering the hierarchical features through the hierarchical vector quantization codebooks, fusing and decoding using a hybrid conditional decoder, and generating a reconstructed image; the encoder model, the decoder model and the hierarchical vector quantization codebook are jointly trained; the input image is encoded into a code stream file through the trained encoder model, and the code stream file is decoded into a reconstructed image through the trained decoder model. The application can realize fine bit rate control and adaptive switching between perceptual and distortion optimization.

The present application relates to the technical field of point cloud processing, and discloses a point cloud compression method, apparatus and device based on a variable bitrate, and a storage medium. The method comprises: acquiring first point cloud data to be compressed and the number of channels between convolution operators; and compressing said first point cloud data by means of a preset convolution model to obtain second point cloud data, wherein the convolution model comprises convolution channels corresponding to the number of channels, and the bitrate of the second point cloud data is associated with the number of channels. According to the present application, when a user has different requirements on the bitrate of a compressed file, a compressed file having a corresponding bitrate can be obtained on the basis of the number of channels between different convolution operators, so that the availability of the compressed file is improved.

The application provides an AVS-based variable code rate control method and device, and relates to the technical field of video coding.The method comprises the following steps: determining a target bit number of an i-th image group in a video sequence; determining a scene switching factor of a previous coded frame adjacent to a to-be-coded frame in the i-th image group; adjusting a target bit number remaining before the to-be-coded frame is coded in the i-th image group based on the scene switching factor of the previous coded frame adjacent to the to-be-coded frame in the i-th image group, the target bit number of the i-th image group, a coded bit number of the previous coded frame adjacent to the to-be-coded frame, a coded bit number in the i-th image group, an actual code rate of a coded stream in the i-th image group, and a frame rate; and determining a target bit number of the to-be-coded frame in the i-th image group.The application has higher scene fitting degree, is good in adaptability to a video sequence with violent motion, frequent scene switching and complex texture, and is low in coding complexity.

The invention relates to a variable code rate compression method, device and equipment and a computer readable storage medium. According to the method, the multi-scale original features of the original image are extracted, and the multi-scale original features are processed through the pre-trained machine vision compression network to obtain the target scale semantic features; obtaining a target color feature of the original image; on the basis of the target scale semantic feature, the target color feature and the noise feature, updating the noise feature until the number of updating times reaches a preset number of times, determining the updated noise feature as a target denoising feature, and optimizing noise and improving feature quality by using semantic and color information; the target denoising feature is processed through the pre-trained human vision compression network to obtain the first target image, so that the bit rate is reduced, transmission and storage resources are saved, machine vision task accuracy and human vision perception quality are both considered, and efficient compression in a man-machine mixed scene is realized.

The application discloses an image compression method, system and storage medium based on continuous variable code rate allocation, and the method comprises the following steps: acquiring an image to be compressed, inputting the image into a trained image continuous variable code rate image compression network, and outputting an image compression result; the image to be compressed is encoded and decoded, and the encoding end comprises the following steps: extracting an image feature value y, using a joint quantization module to perform joint quantization on the channel dimension and the spatial dimension of the image feature value y, and obtaining a quantized feature value; using an arithmetic encoder to encode the quantized feature value into bit stream data; the decoding end comprises the following steps: after the received bit stream data is decoded by an arithmetic decoder, joint dequantization is performed on the channel dimension and the spatial dimension, and a decoded image feature value y is obtained ’ ; the decoded image feature value y ’ is subjected to feature reconstruction, and a reconstructed image is obtained. The application can dynamically control the bit rate during image compression, reduce the bit error rate, and improve the quality of the compressed image.

The application discloses a kind of self-adapting variable code rate's code rate control method.Motion detection method is used to identify the motion, still feature of image block in video frame, and then the motion intensity of video frame is calculated.The motion intensity of video frame is compared with the upper limit threshold of motion intensity, the lower limit threshold of motion intensity set by user, and the pre-allocation encoding bit number of video frame is calculated according to the comparison result and the maximum code rate, minimum code rate, trigger code rate, code rate fall-back smooth step length set by user.The pre-allocation encoding bit number of video frame is corrected according to the encoding state information of video sequence, and the target encoding bit number of video frame is obtained.The target bit control operation is carried out on video frame according to the target encoding bit number of video frame, and the Lagrange multiplier and quantization parameter of video frame are obtained, which are used in the actual encoding process of video frame.The application can flexibly configure different variable code rate control effect through intuitive and easy-to-understand code rate control parameters.

The application provides a high-performance variable code rate image compression method and device, and the specific method comprises the following steps: a segmented network architecture design is adopted, that is, a main encoder-decoder in a basic image compression model is segmented and subdivided into a high code rate network and a low code rate network, wherein a Res_STB module containing two series Swin Transformer network modules is introduced in the high code rate network; a variable code rate encoding feature is obtained by performing variable code rate encoding on a to-be-compressed image through a main encoding network in the image compression model; and image compression is performed based on the variable code rate encoding feature to obtain a compressed image. The method provided by the application is mainly used for solving the problem of performance decline of a single code rate point model converted into a variable code rate model, and has superior performance at each code rate segmentation point.

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 provides a storage device and a method for writing data to the storage device. A method for writing data to a storage device includes determining, by the storage device, a write amplification factor (WAF) value and a fill factor value associated with the storage device in response to a write request; obtaining, by the storage device, a current parity mode value of the storage device; determining, by the storage device, a WAF threshold and a fill factor threshold associated with the current parity mode value; determining, by the storage device, whether to change the current parity mode value to a higher parity mode value of the plurality of parity mode values based on the WAF threshold, the WAF value, the fill factor threshold, and the fill factor value; and writing, by the storage device, data to a storage area of the storage device based on a result of the determination.

The invention discloses a variable-code-rate image coding and decoding method and device. The coding method comprises the following steps: carrying out forward transformation on an input image to obtain a first potential feature; obtaining a second code rate control factor and an index of the second code rate control factor in a code rate control factor index table according to the first code rate control factor; remodeling the second code rate control factor to obtain a code rate control tensor; according to the code rate control tensor, using a modulation parameter generation network to obtain a modulation parameter; modulating the first potential feature by using a modulation parameter to obtain a second potential feature; quantifying the second potential feature to obtain a third potential feature; a coding method based on hyper-prior probability estimation is used for the third potential feature to obtain a first code stream; and putting the index of the second code rate control factor into the first code stream to obtain a second code stream. According to the encoding and decoding method and device, on the premise that the performance is not affected, the current image encoding and decoding method based on deep learning can achieve different encoding and decoding effects in a single-set model mode, various use requirements of users are met, and extra overhead caused by training and storing multiple sets of image encoding and decoding models is avoided.

The present disclosure provides storage device and method for writing data in the storage device. The method for writing data in a storage device includes determining, by the storage device, a Write Amplification Factor (WAF) value and a fill factor value associated with the storage device in response to a write request, fetching, by the storage device, a current parity mode value of the storage device, determining, by the storage device, a WAF threshold and a fill factor threshold associated with the current parity mode value, determining, by the storage device, whether to change the current parity mode value to a higher parity mode value of a plurality of parity mode values based on the WAF threshold, the WAF value, the fill factor threshold, and the fill factor value, and writing, by the storage device, data in a storage area of the storage device based on results of the determining.