15results about How to "Reduce bitrate" patented technology

The embodiment of the invention discloses a discrete voice coding method, electronic equipment and a storage medium, and the method comprises the steps: constructing a voice input and frequency spectrum output VAE, enabling the input voice to have speaker tone disturbance, and enabling the VAE structure to be used for multi-task learning; vector quantization is carried out on the VAE, and a VQ-VAE is initialized, so that a quantization layer is added to continue to reduce an information bottleneck; and additionally training a vocoder, and carrying out waveform reconstruction by starting from the code obtained in the VQ-VAE.

The invention relates to a video processing method and device, a video coding method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-processed video, and segmenting a video frame in the to-be-processed video to obtain coding blocks; calculating the complexity and bit rate error of the coding block; calculating by using the complexity and the bit rate error to obtain an increment quantization parameter; determining a quantization parameter of the frame according to a frame-level code rate control algorithm; calculating a target quantization parameter by using the increment quantization parameter and the quantization parameter of the frame; and performing encoding processing on the encoding block based on the target quantization parameter. And summing the calculated increment quantization parameter and the frame-level quantization parameter to obtain a target quantization parameter. Due to the fact that the contents contained in the coding blocks are different, the corresponding increment quantization parameters are different, when the quantization parameters are utilized to participate in coding, differential coding can be achieved, the coding quality can be guaranteed, meanwhile, the bit rate of unnecessary coding blocks is reduced, and the coding efficiency is improved.

The embodiment of the invention provides a video coding parameter processing method and device, a storage medium and electronic equipment, and the method comprises the steps: inputting a to-be-coded target video frame into a trained just noticeable distortion (JND) prediction model, and obtaining a predicted JND level of each video block in the target video frame; the target video frame is input into a visual attention model, the visual importance level of each video block is obtained, and the visual importance level of each video block is used for representing the visual importance degree of each video block in the target video frame; according to the predicted JND level of each video block and the visual importance level of each video block, adjusting a parameter value of a quantization parameter of each video block to obtain a target parameter value corresponding to each video block; the problem that the visual redundancy estimation accuracy is low in the prior art is solved. The visual redundancy estimation accuracy is improved, and meanwhile, the visual redundancy which is difficult to perceive is eliminated to the maximum extent.

The invention discloses a video coding method based on a double-layer conditional enhancement normalized stream compressor. The video coding method comprises the following steps: S1, inputting a reference frame into a frame interpolator to generate a conditional frame of a basic layer conditional enhancement normalized stream compressor; s2, down-sampling the input high-resolution frame into a low-resolution frame by a down-sampling network; s3, recovering the decoded low-resolution frame of the base layer into a full-resolution frame by the super-resolution reconstruction network; s4, merging the video frame information of the base layer and the predicted forward and reverse motion field information into a high-quality prediction frame; s5, generating a binary skip mask according to the predicted forward and reverse motion field information and the prediction frame; and S6, performing high-quality coding on the target frame by a conditional enhancement normalized stream compressor. According to the method, a low-resolution video frame compressor replaces a full-resolution motion compressor, a motion information compressor is omitted, potential samples needing to be transmitted are reduced through the skip mode coding technology, and the calculation complexity is greatly reduced.

A decoding device according to the present disclosure is a decoding device (100) that decodes core encoded data where a low-band spectrum of a predetermined frequency or lower has been encoded, and extended band encoded data where a high-band spectrum of a predetermined frequency or higher has been encoded based on core encoded data. The decoding device includes: an amplitude normalization unit (103) that normalizes the amplitude of the core decoded spectrum, obtained by decoding the core encoded data, by the largest value of the amplitude of the core decoded spectrum, and generates a normalized spectrum; a noise generating unit (104) that generates a noise spectrum; a first addition unit (105) that adds the noise spectrum to the normalized spectrum and generates a noise-added normalized spectrum; and an extended band decoding unit (106) that decodes the extended band encoded data using the noise-added normalized spectrum, and generates a noise-added extended band spectrum.

An encoding apparatus and method and a decoding apparatus and method are provided. A method for decoding a motion vector according to an embodiment is disclosed, the method comprising the steps of determining at least one PMV candidate block for determining a prediction motion vector of a current block; determining availability of motion vectors of the at least one PMV candidate block; if there is a PMV candidate block determined as unavailable, determining a prediction motion vector of the current block by using a base motion vector (MV); and obtaining a motion vector of the current block based on the determined prediction motion vector.

This invention relates to the field of remote sensing image compression technology, specifically to a remote sensing image compression method based on dual-tree complex wavelet convolution and a frequency dictionary entropy model. The method includes: compressing remote sensing images using a remote sensing image compression model based on dual-tree complex wavelet convolution and a frequency dictionary entropy model; the remote sensing image compression model includes a dual-tree complex wavelet convolution module, a frequency dictionary entropy model module, and a residual feature extraction module; the dual-tree complex wavelet convolution module is used to perform downsampling and upsampling feature processing on the remote sensing image, effectively removing frequency domain redundancy in the latent representation; the frequency dictionary entropy model module is used to perform frequency division on the obtained latent representation of the remote sensing image to establish a probability model; the residual feature extraction module is used to extract features from the remote sensing image, effectively capturing long-range contextual information. This invention enhances the model's image compression effect by introducing dual-tree complex wavelet convolution and a frequency dictionary entropy model, significantly improving the fidelity of remote sensing images at high compression ratios.

The invention relates to a predictive method and apparatus for decoding, a predictive method for encoding, an encoding system, and a computer-readable storage medium. This method comprises the following steps: obtaining adjacent reference pixels at least one edge of the block to be decoded to obtain the first set of adjacent reference pixels; identifying the reference point from at least one edge, and determining the positions of the reference pixels to be selected corresponding to at least one edge according to a predefined number of samples; based on the positions of the reference pixels to be selected, selecting reference pixels corresponding to the positions of the reference pixels to be selected from the first set of adjacent reference pixels, and generating a subset of adjacent reference pixels from the selected reference pixels; and based on the subset of adjacent reference pixels, performing predictive decoding on the block to be decoded.

The embodiment of the invention provides an audio encoding and decoding method and device, and relates to the field of artificial intelligence. An audio encoding method includes: obtaining a time-frequency spectrum of an audio signal; extracting features of a time domain direction and a frequency domain direction based on the time-frequency spectrum of the audio signal by using a first artificial intelligence AI network; and coding the audio signal based on the characteristics of the time domain direction and the frequency domain direction. Optionally, the method performed by the electronic device may be performed using an artificial intelligence model.

The application provides a stereo video compression method with double-branch attention, comprising the following steps: dividing a stereo video into a left video frame sequence and a right video frame sequence; inputting a video frame of the stereo video at time t, a time-adjacent reconstructed frame and a view-adjacent reconstructed frame of the video frame into a DAN stereo video compressor to obtain a video reconstructed frame at time t; wherein the DAN stereo video compressor comprises the following modules: a feature extraction module, a motion estimation module, a disparity estimation module, an LGEDB-based coding and decoding module, a motion compensation module, a disparity compensation module, a double-branch high-frequency information fusion module and an image reconstruction module; and the LGEDB and the DHFFM can realize higher-quality image reconstruction with the same or lower Bits Per Pixel (BPP).

The present invention relates to different frame rate settings. A technique for setting the frame rate of a camera is provided. The camera includes a plurality of image sensors arranged to capture images to be stitched into a panoramic image of a scene. Information is obtained about a corresponding angle between an optical axis of each of the plurality of image sensors and a direction along which a straight path structure to be monitored by the camera extends through the scene. Based on the angle, the plurality of image sensors are divided into at least two groups. All angles of the image sensors within each of the at least two groups are part of its own continuous angle interval. A frame rate is set for each of the at least two groups. The frame rate decreases from the group with the highest continuous angle interval to the group with the lowest continuous angle interval.