Abstract: An image processing method includes: obtaining an input image; performing image conversion processing on the input image by using a generative neural network; and outputting an output image that has been subjected to image conversion processing. The input image has N channels, N being a positive integer greater than or equal to 1; input of the generative neural network includes a noise image channel and N channels of the input image; output of the generative neural network is an output image including N channels.

Abstract: Disclosed are an image classification and conversion method, apparatus, image processor and training method thereof, and medium. The image classification method includes receiving a first input image and a second input image; performing image encoding on the first input image by utilizing n stages of encoding units connected in cascades to produce a first output image, wherein n is an integer greater than 1, and wherein as for 1?i<n, the output of the i-th stage of encoding unit is an input of an (i+1)-th stage of encoding unit, wherein m is an integer greater than 1; outputting a first output image, the first output image comprising mn output sub-images, and each of the mn output sub-images is corresponding to an image category.

Abstract: A super-resolution method, a super-resolution system, a user equipment and a server. The super-resolution method includes: training an image sample at a server; obtaining a server-side image database; updating a local image database in a user device by using the server-side image database; and displaying an input low-resolution image as a high-resolution image.

Abstract: An image processing method, an image processing device and a computer storage medium are provided. The method includes: performing a maximum-filtering processing on an original image and obtaining a luminance channel of the image; and performing a guided-filtering processing on the obtained luminance channel, and estimating and obtaining an incident component.

Abstract: According to embodiments of the present disclosure, a method for processing an adaptive media service at an encoder includes a first acquisition step of acquiring a first data stream including first image encoding data obtained by encoding a first image sequence, a second acquisition step of acquiring at least one second data stream, each second data steam including second image encoding data obtained by encoding a second image sequence and a target optimization parameter corresponding to the second image encoding data, a first selection step of selecting one data stream from a first data stream set in accordance with a condition of the receiver, the first data stream set at least including the first data stream and the at least one second data stream, and a first transmission step of transmitting the selected data stream to the receiver.

Abstract: The disclosure discloses an apparatus for upscaling an image, a method for training the same, and a method for upscaling an image, where a convolutional neural network circuit obtains feature images of the image, a multiplexer upscales the image by integrating every n*n feature images of an input signal into a feature image with a resolution which is n times the resolution of a feature image of the image, where n is an integer greater than 1.

Abstract: A method for adjusting grayscale values of an image includes: for each pixel in the image, calculating a first mapping value for a grayscale value of the pixel in the image through a histogram equalization mapping function; calculating a second mapping value by subtracting a first preset value from the grayscale value of the pixel through the histogram equalization mapping function, and when the result exceeds a preset grayscale range, selecting a minimum value of the preset grayscale range for calculating the second mapping value; calculating a third mapping value by adding a second preset value to the grayscale value of the pixel through the histogram equalization mapping function and when the result exceeds the preset grayscale range, selecting a maximum value of the preset grayscale range; and calculating an output grayscale value of the pixel based on the first, second, and third mapping value and respective weights.

Abstract: A method and an apparatus for installing an application are disclosed. The method comprises: receiving a request to install the application; triggering running of a script to obtain installation information of the selected application and a target virtual environment corresponding to the selected application; processing the installation information of the selected application according to compiling rules and installing rules corresponding to the installation information and the target virtual environment to cause the selected application to be installed into the target virtual environment.

Abstract: There are provided an image processing method and an image processing device. The image processing method comprises: acquiring an input image; acquiring a first noise image and a second noise image; executing image conversion processing on the input image with the first noise image using a generative neural network, to acquire a first output image; and executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to acquire a second output image, wherein the first noise image is different from the second noise image.

Abstract: An image processing method and an image processing device are provided. The image processing method includes steps of extracting a feature of an inputted first image by a first CNN, and reconstructing and outputting an image by a second CNN. The first CNN includes a plurality of first convolutional layers connected sequentially to each other and a plurality of first pooling layers each arranged between respective adjacent first convolutional layers, and each first convolutional layer is configured to generate and output a first convolutional feature. The second CNN includes a plurality of second convolutional layers connected sequentially to each other and a plurality of composite layers each arranged between respective adjacent second convolutional layers, and each composite layer is an up-sampling layer.

Abstract: A training method of a neural network for implementing image style transfer, an image processing method and an image processing device are disclosed. The training method includes: acquiring a first training input image and a second training input image; performing a style transfer process on the first training input image by the neural network to obtain a training output image; based on the first training input image, the second training input image and the training output image, calculating a loss value of parameters of the neural network through a loss function; and modifying the parameters of the neural network according to the loss value, where the loss function satisfies a predetermined condition, obtaining a trained neural network, where the loss function doesn't satisfy the predetermined condition, continuing to repeatedly perform above training process, the loss function including a weight-bias-ratio loss function.

Abstract: The disclosure discloses an apparatus and method for correcting a flicker in a video, and a video device, the method including: determining a correction weight for correcting grayscale values of a current frame of video image according to a ratio of a variance of a histogram of mapped grayscale values of a last frame of video image to a variance of a histogram of grayscale values of the last frame of video image, and a contrast enhancement upper limit parameter input by a user, and/or a largest percentage of the number of pixels with a same grayscale among a total number of pixels in the histogram of the grayscale values of the last frame of video image, and the contrast enhancement upper limit parameter input by the user; and, determining resulting grayscale values of the current frame of video image according to the correction weight.

Abstract: An image upscaling system includes at least two convolutional neural network modules and at least one synthesizer. The convolutional neural network module and the synthesizer are alternately connected to one another. The first convolutional neural network module receive an input image and the corresponding supplemental image, generate a first number of the feature images, and output them to the next synthesizer connected thereto. Other convolutional neural network modules each may receive the output image from the previous synthesizer and the corresponding supplemental image, generate a second number of feature images, and output them to the next synthesizer connected thereto, or output them from the image upscaling system. The synthesizer may synthesize every n*n feature images in the received feature image into one feature image and output the resultant third number of feature images to the next convolutional neural network module connected thereto or output them from the image upscaling system.

Abstract: The present disclosure discloses a method and device for image encoding and a method and device for image decoding. The encoding method comprises steps of: downscaling an input high resolution HR image into a low resolution LR image by a downscaler; compressing the LR image using a first compression method; extracting an index value from at least one of the HR image and the LR image; determining a parameter from a parameter database using the index value; compressing the parameter using a second compression method different from the first compression method; and obtaining a data stream by merging the compressed parameter and the compressed LR image.

Abstract: There are provided an image processing method and an image processing device. The image processing method comprises: acquiring an input image; acquiring a first noise image and a second noise image; executing image conversion processing on the input image with the first noise image using a generative neural network, to acquire a first output image; and executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to acquire a second output image, wherein the first noise image is different from the second noise image.

Abstract: A method for adjusting grayscale values of an image includes: for each pixel in the image, calculating a first mapping value for a grayscale value of the pixel in the image through a histogram equalization mapping function; calculating a second mapping value by subtracting a first preset value from the grayscale value of the pixel through the histogram equalization mapping function, and when the result exceeds a preset grayscale range, selecting a minimum value of the preset grayscale range for calculating the second mapping value; calculating a third mapping value by adding a second preset value to the grayscale value of the pixel through the histogram equalization mapping function and when the result exceeds the preset grayscale range, selecting a maximum value of the preset grayscale range; and calculating an output grayscale value of the pixel based on the first, second, and third mapping value and respective weights.

Abstract: An image processing apparatus and method, an image processing system and a training method are disclosed. The image processing method comprises: receiving an input image; and inputting the input image to K stages of cascaded decoding units, to process the input image to obtain an output image, wherein an ith stage of decoding unit receives mK+1?i input images and outputs mK?i output images, a resolution of the output images is greater than a resolution of the input images, and the number of image components of the output images is less than the number of image components of the input images, where K, i and m are positive integers and 1?i?K.

Abstract: The embodiments of the present disclosure provide an image processing method, and a processing device. The image processing method comprises: acquiring a first image including N components, where N is a positive integer greater than or equal to 1; and performing image conversion processing on the first image using a generative neural network, to output a first output image, wherein the generative neural network is trained using a Laplace transform function.

Abstract: A drowning alarm system and a drowning alarm method. The drowning alarm system includes a submerging detection device, a position detection device and a signal transmitting device. The submerging detection device configured to detect whether or not the submerging detection device is submerged, and generate a submerging alarm instruction when the submerging detection device is submerged. The position detection device configured to determine whether or not the submerging detection device is within a preset range, and generate a distance information instruction when the submerging detection device is within the preset range. The signal transmitting device configured to transmit a first alarm signal when the submerging detection device generates the submerging alarm instruction and the position detection device generates the distance information instruction. The drowning alarming system with false alarm prevention function is realized.

Abstract: The present disclosure provides a method and device for correcting video flicker. The method comprises: performing statistics on grayscale values of a previous frame of video image to obtain a histogram of the grayscale values of the previous frame of video image; determining correction weights for correcting grayscale values of a next frame of video image according to the histogram; and correcting the grayscale values of the next frame of video image according to the correction weights.