80 results about "Compression artifact" patented technology

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

The invention discloses an immersive video enhancement method and device based on frequency domain boundary collaborative optimization, and relates to the field of video processing, and the method comprises the steps: obtaining a to-be-reconstructed compressed multi-view texture and depth video sequence, and inputting the sequence into a trained immersive video enhancement model; a current to-be-enhanced video frame passes through a feature extraction module, and high-frequency features and low-frequency features are extracted respectively; the high-frequency features and the low-frequency features pass through a frequency domain enhancement module to obtain a frequency domain enhanced image; inputting the frequency domain enhancement image and the current video frame to be enhanced into a boundary enhancement module to obtain a fused image; and inputting the fused image and an adjacent video frame of the current to-be-enhanced video frame into a space-time deformable convolution module to obtain an aligned fused image, and performing prediction on the aligned fused image through a quality enhancement module to obtain an enhanced residual error and generate a corresponding reconstructed video. According to the method, the problems of compression artifacts, boundary artifacts, low quality of immersive videos and the like are solved.

The invention provides an image compression artifact removal method based on a frequency domain hybrid expert network, and relates to the field of image processing. The method comprises the following steps: acquiring image data with compression artifacts; extracting shallow image features of the image data through an independent convolutional layer; extracting long-distance dependent image features of the shallow image features through a spatial attention mechanism; based on long-distance dependent image features, inputting the long-distance dependent image features into a frequency domain transformation expert network, and determining an optimal frequency domain transformation expert through parallel processing of multiple frequency domain transformation experts and an expert selection mechanism; processing the long-distance dependent image features through an optimal frequency domain transformation expert to obtain enhanced image features; performing image reconstruction on the enhanced image features to obtain a reconstructed image; the reconstructed image is an image after the compression artifacts are removed. The method is used in an image compression artifact removal process, and solves the technical problem that multiple types of complex compression artifacts are difficult to effectively remove in the prior art.

The invention belongs to the technical field of image processing, and particularly relates to an image tampering detection method fusing noise residual errors and compression artifacts and a program product. According to the scheme, noise residual features of compression artifact features of an original image are extracted through an error level analysis technology and an airspace rich model, and then an image tampering detection model with quality adaptability is constructed by combining the two types of features. The network model firstly extracts tampering features from image compression features and steganography noise dimensions through a convolutional layer in an ELA branch and an SRM branch, and then performs multi-scale feature coding through a lightweight MobileNetV2 network; feature interaction enhancement is realized in combination with an SECA attention mechanism; and finally, generating a pixel-level binary mask representing the tampered area through a feature fusion strategy. According to the scheme, the compression characteristic and the noise characteristic of the image can be fully utilized, and the detection precision of the model on the low-quality image and the robustness in a multi-quality scene are improved.

The invention relates to the technical field of picture compression, and particularly discloses a multi-thread picture compression method and device and a storage medium, and the method comprises the steps: carrying out the feature block division of a to-be-compressed large-size bidding document picture through an image semantic segmentation model, generating division metadata, and executing a dynamic thread distribution strategy based on the division metadata, performing complexity evaluation calculation on each feature block to generate a block complexity score; establishing a thread distribution mapping table according to the complexity scores of the blocks, and starting a multi-stage compression thread group for the blocks with the complexity scores higher than a threshold value; starting a single-thread rapid compression channel for the block with the complexity score lower than a threshold value; performing space coordinate alignment splicing on the compressed blocks through the main thread to generate a spliced compressed image; and packaging and outputting the compressed image after the visual detection processing. The problems of serious compression distortion, low processing efficiency, disordered structure and the like when a traditional compression technology is used for processing a large-size bidding document image are effectively solved.

The invention discloses an image quality evaluation continuous learning method based on a prototype replay strategy, and the method comprises the following steps: constructing an evaluation model based on a compression distortion prototype replay strategy module, an image quality attention contrast learning module, and a loss optimization function and quality feature regression module; storing the distorted picture compact groups of different distortion type prototypes into a memory with a limited size to obtain a training set; acquiring quality features of distorted images in the training set; optimizing the evaluation model to obtain an optimized evaluation model; and training the optimization evaluation model to obtain a final image quality evaluation model. According to the method, the problem that the overall accuracy of the model for the multi-scene image is not high due to the fact that the problem of knowledge disastrous forgetting of different scene distortion types is insufficient to solve can be effectively relieved, and therefore accurate prediction of the quality of different distortion scene images is achieved.

A system and method for real time discrete cosine transform image and video processing with convolutional neural network architecture. The system and method transforms degraded inputs into subband images, which are analyzed by a machine learning classification network to identify specific types of blur and compression artifacts. The classification network dynamically adjusts the parameters of separate DC and AC deblurring networks based on its analysis. This adaptive approach optimizes processing for various degradation types, improving the quality of the reconstructed output. The system and method's real-time capability and enhanced adaptability make it suitable for a wide range of imaging and video applications, offering superior performance over traditional methods.

Methods, systems, and apparatus, including computer-readable storage media for super-resolution upscaling of compressed images with compression artifact restoration. A diffusion model is fine-tuned on randomly compressed images labeled with a corresponding compression quality factor for each image to perform super-resolution upscaling while correcting for compression artifacts in the image. Compressed image training data can be labeled according to a model trained to predict compression quality factors from input compressed images. Model processing of a pixel-based diffusion model can be improved with a consistency model mapping noised images during the diffusion stage of a diffusion model to the original input image. A consistency model and a pixel-based diffusion model can be trained together. Thereafter, the consistency model can be used to generate images from noise in a single step, versus performing multiple steps as in the diffusion stage of the pixel-based diffusion model.

Innovations in machine learning (“ML”) models used in adaptive post-processing of decoded video in a conferencing tool are described. For example, as part of post-processing of decoded video, a super-resolution / video restoration model increases spatial resolution (e.g., by interpolation between sample values), mitigates compression artifacts, and mitigates upscaling artifacts introduced when increasing spatial resolution. Or, as another example, as part of post-processing of decoded video, a video restoration model mitigates compression artifacts, without increasing spatial resolution. For adaptive post-processing, a post-processing model can be selectively applied depending on results of scenario detection, results of segmentation, and / or results of video quality analysis. With the innovations, a conferencing tool can in effect provide video at higher quality without significantly increasing the network bandwidth consumed by the video or, alternatively, provide video using less network bandwidth without significantly hurting the quality of the video.

Innovations in machine learning (“ML”) models used in adaptive post-processing of decoded video in a conferencing tool are described. For example, as part of post-processing of decoded video, a super-resolution / video restoration model increases spatial resolution (e.g., by interpolation between sample values), mitigates compression artifacts, and mitigates upscaling artifacts introduced when increasing spatial resolution. Or, as another example, as part of post-processing of decoded video, a video restoration model mitigates compression artifacts, without increasing spatial resolution. For adaptive post-processing, a post-processing model can be selectively applied depending on results of scenario detection, results of segmentation, and / or results of video quality analysis. With the innovations, a conferencing tool can in effect provide video at higher quality without significantly increasing the network bandwidth consumed by the video or, alternatively, provide video using less network bandwidth without significantly hurting the quality of the video.

Innovations in machine learning (“ML”) models used in adaptive post-processing of decoded video in a conferencing tool are described. For example, as part of post-processing of decoded video, a super-resolution / video restoration model increases spatial resolution (e.g., by interpolation between sample values), mitigates compression artifacts, and mitigates upscaling artifacts introduced when increasing spatial resolution. Or, as another example, as part of post-processing of decoded video, a video restoration model mitigates compression artifacts, without increasing spatial resolution. For adaptive post-processing, a post-processing model can be selectively applied depending on results of scenario detection, results of segmentation, and / or results of video quality analysis. With the innovations, a conferencing tool can in effect provide video at higher quality without significantly increasing the network bandwidth consumed by the video or, alternatively, provide video using less network bandwidth without significantly hurting the quality of the video.

The invention discloses an optimization method and system for compressed point cloud data, equipment and a medium. The method comprises the following steps: acquiring first data and second data; extracting local geometric features and global structural features from the first data; adapting a compression distortion type of the first data according to the coding parameter; based on the local geometric features, determining a deviation range of each discrete point in the first data and a point missing region in the first data; restoring the first data by compressing a restoration network corresponding to the distortion type based on the global structure feature, the deviation range and a point missing region in the first data to obtain second data; the first data and the second data are merged to obtain optimized data, distortion types under different compression strengths can be adapted through the coding parameters, and targeted restoration and optimization of the compressed point cloud data are realized in combination with local and global features, so that the geometric fidelity and visual quality of the compressed point cloud data are improved.

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

Innovations in machine learning ("ML") models used in adaptive post-processing of decoded video in a conferencing tool are described. For example, as part of post-processing of decoded video, a super-resolution / video restoration model increases spatial resolution (e.g., by interpolation between sample values), mitigates compression artifacts, and mitigates upscaling artifacts introduced when increasing spatial resolution. Or, as another example, as part of post-processing of decoded video, a video restoration model mitigates compression artifacts, without increasing spatial resolution. For adaptive post-processing, a post-processing model can be selectively applied depending on results of scenario detection, results of segmentation, and / or results of video quality analysis. With the innovations, a conferencing tool can in effect provide video at higher quality without significantly increasing the network bandwidth consumed by the video or, alternatively, provide video using less network bandwidth without significantly hurting the quality of the video.

The application provides a compression artifact suppression method combined with multi-level interframe correlation. The method mainly relates to a means combining multi-level motion compensation and deep convolution mapping to perform quality enhancement on HEVC decoded video. The application mainly utilizes the characteristics of interframe correlation of the video, and then designs a multi-level motion compensation network to perform motion compensation on two adjacent frames of a current frame, and then fuses features of the current frame with the two adjacent frames. Then, attention feature extraction is performed on the current frame and the fused multi-frame feature map respectively. Finally, deep residual learning and cross-layer cascade are performed to realize deep fusion, mapping and reconstruction of multi-level features, so that quality enhancement of the current frame is realized.

The application discloses an adaptive image preprocessing method and device based on intra block copy and a medium. The application obtains a reconstructed image of a coded region, inputs the reconstructed image into a classifier for judgment processing, and obtains a judgment processing result. When the judgment processing result indicates that preprocessing is needed, the reconstructed image is subjected to image enhancement processing to obtain an enhanced image, which is beneficial to improving compression artifacts of the reconstructed image. The application obtains a first real probability corresponding to the reconstructed image and a second real probability of the enhanced image, determines a final image according to the first real probability and the second real probability to replace the reconstructed image, or obtains a first pixel mean value of the reconstructed image and a second pixel mean value of the enhanced image, and determines a final image according to the first pixel mean value and the second pixel mean value to replace the reconstructed image. The final image with better image quality can be used as a reference block, which can effectively improve prediction accuracy and coding efficiency, and can be widely applied to the field of video coding.

Systems and techniques are generally described for selecting a machine learning model for compression artifact removal and resolution upscaling of video streaming data. In various examples, a system or method receives a stream of video data, determines a category of the stream of video data based at least partially upon a compression level of the stream of video data, selects weights for a machine learning model based upon the category, and executes the machine learning model with the selected weights to remove compression artifacts in the stream of video data and upscale a resolution of the stream of video data.

A system and method for complex-valued radar image compression integrates AI-based techniques to enhance compression quality. It incorporates a novel AI deblocking network composed of convolutional layers for feature extraction and a channel-wise transformer with attention to capture complex inter-channel dependencies. The convolutional layers extract multi-dimensional features from the complex-valued radar image, while the channel-wise transformer learns global inter-channel relationships. This hybrid approach addresses both local and global features, mitigating compression artifacts and improving image quality. The model's outputs enable effective complex-valued radar image reconstruction, achieving advanced compression while preserving crucial information for accurate analysis.

The embodiment of the invention discloses a compressed video quality enhancement method based on deep learning, and relates to the technical field of computer vision, the method comprises the following steps: extracting each video frame in a compressed video frame by frame as a target video frame, and processing based on each target video frame to obtain a compressed video frame sequence; inputting each compressed video frame sequence into the trained compressed video quality enhancement model to obtain a residual error corresponding to the compressed video frame sequence; adding the residual error and a target video frame in the compressed video frame sequence to obtain a corresponding enhanced video frame; and outputting an enhanced video corresponding to the compressed video by combining the enhanced video frame corresponding to each compressed video frame sequence. According to the method, the compression artifacts at the boundary of the moving object can be effectively removed, the artifact removal performance of other areas can be kept, the quality of the compressed video can be remarkably improved, and the defect caused by the fact that the image quality becomes poor due to the compressed video is avoided.

Various embodiments of transcoding system that includes a pre-filtering system are disclosed. The pre-filtering system includes amorphous sub-filter modules and is configured to automatically configure a sequence of filter modules to be used to filter a given segment of a media object being transcoded based on artifacts resulting from an earlier decoding process. The pre-filtering system does not require prior knowledge of what encoding parameters that were used to encode the media object being transcoded. Also, the filtering system supports a wide variety of encoding formats and can automatically adjust the filtering sequence and / or filtering parameters based on the variability of compression artifacts resulting from the decoding of media objects previously encoded using a plurality of encoding formats and / or encoding parameters.

The present invention discloses a super-resolution method for compressed videos based on a deep feature fusion network. The method mainly includes the following steps: for the input low-resolution compressed video sequence, five consecutive frames are used as the input of the network, and a hybrid convolution block and a residual block are used to extract low-dimensional feature information; the ordinary differential equation block in the restoration module is used to reduce compression artifacts and obtain high-dimensional feature information; different-dimensional feature maps are fused and input into the reconstruction module, and super-resolution reconstruction is completed by using an adaptive channel attention and pixel attention module and a sub-pixel convolutional layer for upsampling to obtain high-resolution target video frames; training samples are constructed in the video dataset, the network is trained, and the final model is obtained. The method of the present invention is used to reconstruct a low-resolution compressed video into a high-resolution video, and is an effective super-resolution reconstruction method for compressed videos.

The invention provides a video filtering method and device, electronic equipment and a computer program product, and relates to the technical field of video coding. The method comprises the following steps: acquiring a video frame to be processed, wherein the video frame to be processed comprises a plurality of coding units; determining a first filtering video frame obtained after the to-be-processed video frame is subjected to first filtering processing and filtering distortion, and determining compression distortion generated after the first filtering video frame is subjected to image coding processing; obtaining a reference frame number corresponding to the to-be-processed video frame; and according to the reference frame number, the filtering distortion and the compression distortion, respectively determining a frame bit weight of the to-be-processed video frame and a unit bit weight of the coding unit, the frame bit weight and the unit bit weight being used for second filtering processing of the video. According to the invention, the influence of the filtering process on the video frame is fully considered, and the problem that the weight factor adopted by the subsequent filtering process has an error due to the introduction of the filtering operation is corrected.

Systems and methods are provided herein for efficient, reproducible noise sampling coordinate generation for texture synthesis in image and video processing. The techniques enable high-quality film grain or texture synthesis as a post-processing step in video decoders, masking compression artifacts and restoring perceptual quality. Hash-based mapping, including direct coordinate mapping and linear index hashing, can be used to generate coordinates for noise sampling by hashing image block coordinates and a seed with preselected constants to generate sampling positions. Shuffled permutation sampling can be used to generate coordinates by generating and shuffling a list of template coordinates using a seeded pseudo-random number generator, and assigning unique positions to each block. Wrap-around addressing, including treating the noise template as a toroidal space, can be used to maximize coverage and eliminate edge bias. The disclosed techniques provide deterministic, hardware-friendly, and unbiased sampling.

The present invention provides a method for enhancing virtual view quality based on asymmetric streaming, comprising the following steps: S1: extracting shallow features from a low-quality input virtual view; S2: inputting the shallow features into a hybrid codec to convert them into deep features; S3: adaptively fusing the features output by each MSACB module at the decoding end of the hybrid codec; and S4: reconstructing a quality-enhanced virtual view based on the low-quality virtual view and the fused features. This method, based on asymmetric streaming, addresses the current problems of compression distortion and DIBR distortion in 3D video transmission.

An example system includes a feature extraction engine to identify features in a compressed image at a plurality of scales. The features include features corresponding to compression artifacts and features corresponding to image content to be upsampled. The feature extraction engine is to identify the features in the compressed image at a first scale based on noncontiguous pixels. The system also includes a reconstruction engine to refine the features corresponding to the image content to be upsampled and mitigate the features corresponding to the compression artifacts. The system includes an upsampling engine to generate an upsampled version of the compressed image based on the refined and mitigated features.

Systems and techniques are generally described for selecting a machine learning model for compression artifact removal and resolution upscaling of video streaming data. In various examples, a system or method receives a stream of video data, determines a category of the stream of video data based at least partially upon a compression level of the stream of video data, selects weights for a machine learning model based upon the category, and executes the machine learning model with the selected weights to remove compression artifacts in the stream of video data and upscale a resolution of the stream of video data.

The invention relates to the technical field of artificial intelligence and image processing, can be applied to the field of intelligent medical treatment and finance, and discloses a depth forgery detection method, device, equipment and medium, and the method comprises the steps: carrying out the preprocessing of a to-be-detected UGC video, and carrying out the feature extraction of a preprocessed video frame sequence, and obtaining a multi-scale feature map; calculating compression artifact intensity and noise level of the multi-scale feature map; according to the compression artifact intensity and the noise level, dynamically adjusting weights of a plurality of different pre-training tasks used for deep forgery detection in a pre-training task pool, and generating a pre-training task combination; dynamically weighting the features of each activated pre-training task in the pre-training task combination based on a gating attention mechanism to obtain multi-task fusion features; and performing forgery detection on the multi-task fusion feature by using a local window attention mechanism and a global deformable attention mechanism based on a hierarchical visual converter to obtain a forgery probability with uncertainty calibration.

The application discloses an image recovery method and system, utilizes three different image recovery models of a deformation convolution attention network, a non-local enhancement network and a high-frequency enhancement double-branch network to better recover details and texture information of a damaged image, and through application of the three different image recovery models to common image recovery tasks, including synthetic noise removal, real image denoising, compression artifact removal and real image super-resolution, the advancement can be verified.

Innovations in machine learning ("ML") models used in adaptive post-processing of decoded video in a conferencing tool are described. For example, as part of post-processing of decoded video, a super-resolution / video restoration model increases spatial resolution (e.g., by interpolation between sample values), mitigates compression artifacts, and mitigates upscaling artifacts introduced when increasing spatial resolution. Or, as another example, as part of post-processing of decoded video, a video restoration model mitigates compression artifacts, without increasing spatial resolution. For adaptive post-processing, a post-processing model can be selectively applied depending on results of scenario detection, results of segmentation, and / or results of video quality analysis. With the innovations, a conferencing tool can in effect provide video at higher quality without significantly increasing the network bandwidth consumed by the video or, alternatively, provide video using less network bandwidth without significantly hurting the quality of the video.

Existing digital image color style transfer encoding methods are often forced to compromise between performing artifact-free local image processing and performing sufficiently expressive global image processing. Moreover, such existing image style encoding methods may be under-constrained (thereby producing more visible artifacts in stylized output images than would be desired) or over-constrained (and thereby not being expressive enough to sufficiently learn and reproduce local / spatial color changes in the stylized output images). Thus, disclosed herein are techniques to combine the advantageous aspects of existing image stylization methods in a novel hybrid image processing method that effectively bifurcates the learning and reproduction of pixel luminance changes from the learning and reproduction of pixel color changes in stylized output images. Such techniques may also advantageously capture local color changes without introducing excessive compression artifacts in the generated stylized output images—while still performing the color style transfer image processing operations in a computationally-efficient fashion.