999 results about "Filter (video)" patented technology

A long video understanding method based on iterative hierarchical key frame selection comprises the following steps: firstly, carrying out hierarchical frame sampling on an input video to obtain hierarchical visual features, and then carrying out a key frame query module on the Nth-layer visual features of a video frame and an input problem text to obtain a key frame query result; video key frame query is carried out in combination with context semantics to generate query vectors, whether the query vectors are enough to generate answers to the input questions is predicted, if not, the query key frames are updated in the (N + 1) th layer of visual features with the higher frame rate, and the input question texts are combined with the context semantics to carry out iterative query of the key frames again; and inputting the inquired key frame and the instruction or the question into a multi-mode large model to generate an understanding result. According to the method, the video frames are queried and the associated frames are screened out based on the user input problem, so that the performance and efficiency of long video understanding are improved, and the method has wide application prospects in scenes such as entertainment, security and education.

A method implemented by a video coding apparatus. The method includes applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample. The NN filter includes an NN filter model generated based on partitioning information of the video unit. Usage of the NN filter is indicated by one or more syntax elements in a bitstream. A conversion is performed between a video media file and a bitstream based on the filtered sample.

A method for video decoding is provided. The method includes obtaining, from a video bitstream, a coding unit in a current picture, wherein the coding unit comprises a luma block and at least one chroma block; and in response to a determination that reconstructed luma samples in the luma block are not to be down-sampled: determining one or more cross-component prediction models based on a luma filter, wherein the one or more cross-component prediction models comprise a convolutional cross-component model (CCCM); obtaining, based on the luma filter, at least one reconstructed luma sample in the luma block that corresponds to a chroma sample in the at least one chroma block; and applying at least one of the one or more cross-component prediction models to the at least one reconstructed luma sample to predict the chroma sample.

Methods for video decoding and encoding, apparatuses and non-transitory computer-readable storage media thereof are provided. In one method for video decoding, a decoder may obtain a plurality of prediction blocks based on a current inter coding block; obtain a current template of the current inter coding block, wherein the current template comprises a plurality of reconstructed samples neighboring to the current inter coding block; obtain a plurality of template predictions of the current template respectively corresponding to the plurality of prediction blocks of the current inter coding block; obtain at least one filter based on the plurality of template predictions and the current template; and obtain a filtered block based on the at least one filter and the plurality of prediction blocks.

Implementations of the disclosure provide a video processing apparatus and method for performing intra prediction on a video block. The video processing method may include receiving, by a processor, reference samples from a video frame of a video comprising the video block. The video processing method may further include determining, by the processor, a reference sample filter based on a size of each video block. The reference sample filter is among a plurality of reference sample filters each derived for a different video block size. The video processing method may also include applying, by the processor, the determined reference sample filter to the received reference samples. The video processing method may additionally include performing, by the processor, the intra prediction on the video block using the filtered reference samples.

A method and an apparatus are disclosed for video coding using an improved inloop filter for chroma components. In the disclosed embodiments, a video decoding device performs obtaining a reconstructed frame that includes luma samples and chroma samples, subsequently obtaining a scale value representing a resolution difference between the reconstructed frame and an original frame. Responsive to the reconstructed frame having a resolution that is based on the scale value and is less than a resolution of the original frame, the video decoding device generates an upsampled chroma frame by inputting the luma samples and the chroma samples into a cross component resampling inloop filter (CC-RIF).

A method of decoding video data performed by an electronic device is provided. The method receives the video data and determines a block unit from a current frame included in the video data. The method determines a first chroma prediction block of the block unit based on a luma vector of the block unit, and determines a second chroma prediction block of the block unit using a cross-component filter based on a reconstructed luma block of the block unit. The method determines, from the video data, a weighting index for selecting, from multiple predefined parameters, multiple weighting parameters of the first chroma prediction block and the second chroma prediction block based on the weighting index. The method reconstructs the block unit based on the first chroma prediction block, the second chroma prediction block, and the weighting parameters.

A video analysis system trains and uses a machine-learned adaptive thresholding model configured to receive a query (e.g., text, image, video), and generate a predicted threshold value for a corresponding video retrieval model that indicates what value the filtering threshold should be for the query. The video analysis system filters video segments for the query that are associated with relevance scores above the predicted threshold generated by the adaptive thresholding model. In one instance, the adaptive thresholding model is configured as a machine-learned model, including neural networks, embedding models, transformer-based architectures, and the like that are capable of generating a predicted threshold value given a query that includes, for example, text, images, videos, audio, or any other appropriate data modality.

The invention relates to the technical field of panoramic video processing, in particular to a panoramic video stability enhancement method based on space-time consistency, which comprises the following steps: acquiring a panoramic video frame sequence; obtaining spherical projection coordinates of each frame in the panoramic video frame sequence; based on the spherical projection coordinates, a deep learning model is constructed, and the deep learning model comprises a feature extraction encoder and a motion prediction compensation decoder; performing feature extraction on the panoramic video frame sequence by using a feature extraction encoder; performing motion prediction and compensation by using a motion prediction compensation decoder based on a feature extraction result; constructing a space-time filter according to the motion prediction and compensation result, and smoothing the motion vector; based on the smoothed motion vector, performing multi-frame motion analysis by using a long time sequence network; according to a multi-frame motion analysis result, designing panoramic video optical flow motion estimation; performing stable enhancement processing on the panoramic video frame sequence based on an optical flow motion estimation result; and outputting the stably enhanced panoramic video.

Methods for video decoding and encoding, apparatuses and non-transitory computer-readable storage media thereof are provided. In one method for video decoding, a decoder may obtain a motion compensated chroma sample and a plurality of motion compensated luma samples for a current inter coding block. Furthermore, the decoder may obtain an adaptive cross-component filter and obtain a filtered motion compensated chroma sample based on the adaptive cross-component filter, the motion compensated chroma sample, and the plurality of motion compensated luma samples.

A method for using Extrapolation Intra Prediction (EIP) to code pixel blocks is provided. A video coder receives data to be encoded or decoded as a current block of pixels of a current picture of a video. The video coder inherits a previously used linear model for extrapolation intra prediction (EIP) that is derived based on samples in a template region neighboring a previously coded block, the template region occupying an area that extends beyond at least one of top and left edges of the previously coded block. The video coder applies the inherited linear model to generate a predictor of the current block by using reconstructed samples or predicted samples of the current block as input to a filter to generate samples of the predictor. The video coder encodes or decodes the current block by using the predictor.

The present disclosure provides a method for decoding video data, comprising: obtaining a video block from a bitstream, obtaining internal luma sample values of the video block, external luma sample values and external chroma sample values of an external region of the video block, determining, by using values based on the external luma sample values and the external chroma sample values, a set of weighting coefficients corresponding to a filter shape, wherein the filter shape and the set of weighting coefficients are configured for predicting a chroma sample value based on a plurality of corresponding luma sample values, and the values comprise non-downsampled values of the external luma sample values, or the non-downsampled values of the external luma sample values along with a downsampled value of at least one of the external luma sample values, predicting, with the filter shape and the set of weighting coefficients, internal chroma sample values of the video block based on the internal luma sample values, and obtaining decoded video block using the predicted internal chroma sample values.

In one embodiment, a method includes maintaining a video communication between two or more client devices with each client device comprising cameras and being associated with a respective video stream in the video communication, determining scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices, determining a privacy filter to apply to a first video stream associated with the first client device based on the scene data, and providing instructions to apply the privacy filter to the first video stream in the video communication.

A mechanism for processing video data is disclosed. A filter is applied to a video unit. The filter employs an extended tap for a first sample in the video unit and a spatial tap for a second sample in the video unit. A conversion is performed between a visual media data and a bitstream based on the video unit.

Systems and methods are provided herein for only including portions of a user's environment that have been approved by a user in a video conference while excluding portions that have not been approved. This may be accomplished by a device receiving a policy identifying one or more approved objects of a scene of a video stream. The device may then generate a filtered video stream by only including portions of the scene that comprise the one or more objects that were approved by the policy in the filtered video stream. The filtered video stream may be combined with other video streams to generate a video conference that is transmitted and / or stored by one or more devices participating in the video conference.

Techniques are described herein for processing video data using enhanced interpolation filters for intra-prediction. For instance, a device can determine an intra-prediction mode for predicting a block of video data. The device can determine a type of smoothing filter to use for the block of video data, wherein the type of the smoothing filter is determined based at least in part on comparing at least one of a width of the block of video data and a height of the block of video data to a first threshold. The device can further perform intra-prediction for the block of video data using the determined type of smoothing filter and the intra-prediction mode.

The invention relates to the technical field of image stitching, and discloses a video transmission high-definition image intelligent stitching method and system. The system comprises an image preprocessing module, a feature point matching and screening module, an image optimal splicing seam generation module and a video output module. The method comprises the following steps: firstly, acquiring a video, carrying out dynamic range equalization, carrying out filtering processing by using an adaptive noise reduction method, and carrying out image correction; secondly, extracting feature points by using a self-adaptive corner detection algorithm, matching the feature points based on a multi-dimensional spatial data index to obtain feature point matching pairs, and screening the feature points; searching an overlapping region, and introducing a dynamic search algorithm to generate an optimal image splicing path to obtain an optimal image splicing seam; and finally, dividing the image according to the dynamic grid, and realizing video output by using priority ranking. According to the method, the video images are processed and spliced, the purpose of intelligent image splicing is achieved, and the method is accurate and objective.

Embodiments of the present disclosure provide a method for video processing. The method comprises: obtaining, during a conversion between a current chroma block of a video and a bitstream of the video, the number of lines for determining at least one filter coefficient for a convolutional cross-component model (CCCM) for the current chroma block; and performing the conversion based on the number of lines. Compared with the conventional solution, the proposed method can advantageously improve coding efficiency.

The embodiments relate to a method for encoding / decoding. The encoding method (900) comprises receiving a video sequence (1505) comprising a first frame and a second frame; encoding (1510) the first frame into a first coded frame using a first coding method (901); reconstructing (1515) a first decoded frame corresponding to the first coded frame; deriving (1520) one or more optimizing parameters to adjust a traditional filter (1110), wherein the optimizing parameters reduce distortion of the first decoded frame to produce a first filtered frame; filtering (1525) the first decoded frame with the traditional filter (1010, 1110); encoding (1530) the second frame into a second coded frame by a second set of algorithms of the second coding method (906, 1210) and by using the first filtered frame directly or indirectly for prediction; and signalling (1535) said one or more optimizing parameters. The embodiments also relate to apparatuses for encoding / decoding.

Syntax elements allow to enable applying film grain using a neural network post-processing filter. Syntax elements define parameters related to the film grain neural network post- processing filter. An encoded video bitstream carries such syntax elements from an encoding device to a decoding device, thus allowing the encoding device to specify how to apply film grain using a neural network post-processing filter and the decoding device to apply the film grain neural network post-processing filter when displaying the decoded video. Additional syntax elements specify parameters comprising a film grain style, a film grain intensity, a film grain purpose or a region of interest where to apply the film grain.

A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising a current picture including a sub-picture coded according to inter-prediction. A motion vector for a block of the sub-picture is determined. A clipping function is applied to sample locations in a reference block to support application of an interpolation filter when the motion vector points outside of the sub-picture and when a flag is set to indicate the sub-picture is treated as a picture. The interpolation filter is applied to results of the clipping function to obtain a predicted sample value. The block is decoded based on the predicted sample value. The block is forwarded for display as part of a decoded video sequence.

A method for decoding video data. The method comprises: obtaining, from a bitstream, a video block and filter shape information; determining a region to derive a multiple linear regression (MLR) model; obtaining luma and chroma sample values in the region; deriving the MLR model using the luma and chroma sample values in the region based on the filter shape information; predicting each of chroma samples in the video block by applying the MLR model to corresponding luma samples for that chroma sample based on the filter shape information; and obtaining decoded video block using the predicted chroma samples.

A method for in-loop sample offset filtering in a video decoder is disclosed. The method includes obtaining at least one statistical property associated with reconstructed samples of at least a first color component in a current reconstructed data block of a video stream, selecting a target sample offset filter among a plurality of sample offset filters based on the at least one statistical property, the target sample offset filter comprising a nonlinear mapping between sample delta measures and sample offset values, and filtering a current sample in a second color component of the current reconstructed data block using the target sample offset filter and reference samples in a third color component of the current reconstructed data block to generate a filtered reconstructed sample of the current sample.

A video coder may receive video data, and apply a filter to a plurality of categories of samples of the video data. The plurality of categories of samples may include two or more of an input of a fixed filter, an output of the fixed filter, an input of a signaled filter, an output of the signaled filter, an input of an adaptive loop filter, an output of the adaptive loop filter, an input of a sample adaptive offset (SAO) filter, an output of the SAO filter, an input of a bilateral filter, an output of the bilateral filter, an input of a cross component SAO filter, an output of the cross component SAO filter, an input of a deblocking filter, an output of the deblocking filter, filtered reconstructed residual data, dequantized coefficients, filtered dequantized coefficients, a predictor, or a filtered predictor.

The present invention discloses a video frame image denoising method, device, storage medium and program product, which relates to the field of video image processing technology. The method comprises: performing spatial domain denoising on the current frame image in color space to obtain an intermediate image; performing motion compensation on the denoised image of the previous frame based on the intermediate image to obtain a compensated frame image; determining a compensation error based on the compensated frame image and the current frame image; determining the estimated noise of the current frame image based on the intermediate image and the current frame image; determining the filter coefficient of the time domain filter based on the estimated noise and the compensation error; performing time domain denoising on the current frame image based on the time domain filter to obtain a denoised image corresponding to the current frame image. Using the scheme provided by the present application, the video frame image is first subjected to spatial domain denoising and then subjected to time domain denoising, and the denoising effect is effectively improved by taking into account the influence of the random characteristics of inter-frame noise.

An example method of video coding includes receiving a video bitstream comprising a plurality of frames, including a current frame comprising a current block. The method also includes determining an edge direction by performing edge detection for the current block, and determining a difference between a current sample of the current block and a neighboring sample based on the edge direction. The method further includes applying a filter to the current block based on the determined difference.

The invention discloses a production line multi-source heterogeneous stream data acquisition system, and the system comprises a video data preprocessing module which intercepts continuous frames from a video and extracts effective features from the video frames; the time synchronization module is used for uniformly managing timestamps of the multi-source heterogeneous data and identifying a time sequence relationship among the data; the protocol analysis module is used for analyzing the data frame of the communication protocol and carrying out effective data interaction with different devices or systems; the data fusion module is used for integrating the data into a unified data system model; the data storage module is used for collecting, processing and distributing data in real time; and the data display module provides data display, dynamically screens and filters data, and has an alarm function. The problem that data timestamps are inconsistent is effectively solved, all collected data can be compared and analyzed under the unified time reference, diversified data formats from different devices and systems are efficiently processed, and integration and unified management of multi-source heterogeneous data are achieved.

A device for decoding video data determines a pre-filtered reconstructed block of video data; applies one or more of a deblocking filter or a sample adaptive offset filter to the pre-filtered reconstructed block to determine a filtered reconstructed block; applies an adaptive loop filter (ALF) to the filtered reconstructed block to determine a final filtered reconstructed block, wherein to apply the ALF to the filtered reconstructed block, the device is further configured to determine a difference value based on a difference between a value of a current sample of the filtered reconstructed block and a value of a pre-filtered neighboring sample; apply a filter to the difference value to determine a sample modification value; and determine a final filtered sample value based on the sample modification value.

Methods and apparatuses for video decoding and video encoding and a method of processing visual media data are disclosed. The apparatus for video decoding includes processing circuitry that receives coded information indicating that a current block in a current picture is coded with a decoder-side intra mode derivation (DIMD) mode. A template of the current block includes reconstructed samples in the current picture and is adjacent to the current block. The template includes one of a left template and a top template. The processing circuitry determines a filter type from a plurality of filter types associated with the one of the left template and the top template, applies the DIMD mode to the template based on the determined filter type to determine one or more intra prediction modes for the current block, and reconstructs the current block according to the one or more intra prediction modes.

Embodiments of the disclosure provide a solution for video processing. A method for video processing is proposed. The method includes: generating, for a conversion between a video unit of a video and a bitstream of the video unit, a sample value of a first color component of the video unit that is corresponding to a sample of a second color component by applying a plurality of filters to at least one sample of the first color component; and performing the conversion based on the generated sample value.