Abstract: A video image de-interlacing method is provided. The method-includes: acquiring a single frame of original video image; extracting odd field data and even field data in an original video image; performing N-1 times of down-sampling on the odd field data to obtain N-1 odd field data with different resolutions and performing N-1 times of down-sampling on the even field data to obtain N-1 even field data with different resolutions; combining odd field data and even field data with the same resolution to obtain a down-sampled image; and inputting the original video image and the down-sampled image to the de-interlacing network for de-interlacing.

Abstract: A computer-implemented method is provided. The computer-implemented method includes rendering a dynamic effect to one or more objects in an image. The method includes setting boundary points surrounding a foreground object to define a boundary area in which a dynamic movement is to be realized; setting a movement line to define a dynamic movement direction along which the dynamic movement is to be realized, wherein setting the movement line includes detecting a continuous touch over different positions on the touch control display panel; setting a stationary area to define an area in which the dynamic movement is prohibited, wherein setting the stationary area includes detecting a first touch area corresponding to the stationary area on the touch control display panel; and generating an animation of the foreground object in the boundary area moving along the dynamic movement direction, thereby realizing the dynamic effect in the image.

Abstract: The present disclosure generally relates to the field of deep learning technologies. An apparatus for generating a plurality of correlation images may include a feature extracting unit configured to receive a training image and extracting at least one or more of feature from the training image to generate a first feature image based on the training image; a normalizer configured to normalize the first feature image and generate a second feature image; and a shift correlating unit configured to perform a plurality of translational shifts on the second feature image to generate a plurality of shifted images, correlate each of the plurality of shifted images with the second feature image to generate the plurality of correlation images.

Abstract: The present disclosure relates to an image processing method and device, a camera component, an electronic device, and a storage medium. The component includes a first camera module sensing first-band light to generate a first image, a second camera module sensing the first-band light and second-band light and generating a second image, an infrared light source emitting the second-band light and a processor. The second image includes a bayer subimage and an infrared subimage. The processor is coupled with the first camera module, the second camera module and the infrared light source respectively. The processor is configured to perform image processing on at least one of the bayer subimage or the infrared subimage and the first image.

Abstract: The present invention provides a maleate, phosphate, sulfate, hydrochloride of a cyclohexane derivative, N?-[trans-4-[2-[7-(benzo[b]thiophene)-7-piperazinyl]ethyl]cyclohexyl]-N,N-dimethylurea, as shown in Formula I and crystal forms thereof. The crystal forms have low hygroscopicity and good stability and are convenient for long-term storage and transportation; or the crystal forms have a long half-life in vivo, high bioavailability and small individual difference, and thus have obvious clinical application advantages.

Abstract: A method and a system for converting a font of a Chinese character in an image, a computer device and a medium are disclosed. A specific implementation of the method includes: acquiring a stroke of a to-be-converted Chinese character in the image and spatial distribution information of the stroke; and generating a Chinese character in a target font that corresponds to the to-be-converted Chinese character in the image according to the stroke of the to-be-converted Chinese character, the spatial distribution information of the stroke and standard stroke information of the target font, to replace the to-be-converted Chinese character.

Abstract: Magnetic resonance imaging according to the present invention includes T1, T2, or diffusion mapping with improved image resolution. The improved image resolution is achieved by leveraging the delay in the image acquisition to remove the partial volume effect of fluid in and around the tissue being imaged.

Abstract: A computer-implemented method of training a convolutional neural network configured to morph content features of an input image with style features of a style image is provided. The computer-implemented method includes selecting a training style image; extracting style features of the training style image; selecting a training content image; extracting content features of the training content image; processing the training content image through the convolutional neural network to generate a training output image including the content features of the training content image morphed with the style features of the training style image; extracting content features and style features of the training output image; computing a total loss; and tuning the convolutional neural network based on the total loss including a content loss, a style loss, and a regularization loss.

Abstract: Embodiments of the disclosure provide a method for detecting bad points in a video, including: performing extreme filtering respectively on first, second and third frames of images which are sequentially and continuously in the video to obtain first, second and third filtered images, respectively; wherein the extreme filtering is one of maximum filtering and minimum filtering; determining first and second difference images according to the first, second and third filtered images; determining a candidate image according to the first and second difference images; and determining that at least part of points in the second frame of image corresponding to the valid point in the candidate image are bad points. The embodiment of the disclosure also provides a device and a computer-readable medium for detecting bad points in the video.

Abstract: Antibodies are provided which comprise at least one Fab portion that binds CD47 and at least one Fab portion that binds the tumor associated antigen (TAA) CD20; wherein the Fab portion that binds CD47 exhibits low affinity for CD47; and, wherein the Fab portion that binds CD20 exhibits high affinity for CD20; and, wherein the antibody selectively binds CD47 and blocks CD47 interaction with SIRP? in tumor cells while exhibiting no substantial binding to CD47 in normal cells.

Abstract: A video enhancement method and apparatus, an electronic device, and a storage medium are described. The method comprises: extracting features from M frames of images, so as to obtain at least one first-scale image feature (S310); for each first-scale image feature, performing N-level down-sampling processing on the first-scale image feature, so as to obtain a second-scale image feature (S320); performing N-level up-sampling processing on the second-scale image feature, so as to obtain a third-scale image feature (S330), wherein the input of ith-level up-sampling processing is an image feature obtained after performing superimposition processing on the output of (N+1?i)th-level down-sampling processing and the output of (i?1)th-level up-sampling processing, and the multiple of jth-level up-sampling is the same as the multiple of (N+1?j)th-level down-sampling; and performing superimposition processing on the third-scale image feature and the first-scale image feature.

Abstract: A method for processing an image is provided, including: acquiring an input image; performing down-sampling and feature extraction on the input image by an encoder network to obtain multiple feature maps; and performing up-sampling and feature extraction on the multiple feature maps by a decoder network to obtain a target segmentation image; processing levels between the encoder network and the decoder network for outputting feature maps with the same resolution are connected with each other, and the encoder network and the decoder network each includes one or more dense calculation blocks, and at least one convolution module in any dense computation block includes at least one group of asymmetric convolution kernels.

Abstract: The present disclosure provides a training method for generative adversarial network, which includes: extracting a first-resolution sample image from a second-resolution sample image; separately providing a first input image and a second input image for a generative network to generate a first output image and a second output image respectively, the first input image including a first-resolution sample image and a first noise image, the second input image including the first-resolution sample image and a second noise image; separately providing the first output image and a second-resolution sample image for a discriminative network to output a first discrimination result and a second discrimination result; and adjusting parameters of the generative network to reduce a loss function. The present disclosure further provides an image processing method using the generative adversarial network, a computer device, and a computer-readable storage medium.

Abstract: Provided are a method for enhancing a video resolution enhancement, a computer readable storage medium, and an electronic device. The method includes: obtaining multiple image frames as input data, and obtaining initial data by performing feature extraction on the input data using a first three-dimensional convolutional layer; obtaining first feature data by performing down-sampling on the initial data at a preset multiple; obtaining first reference data by performing a convolution operation on the first feature data using a second three-dimensional convolutional layer to merge the first feature data as one frame; and obtaining first output data by performing up-sampling on the first reference data at the preset multiple.

Abstract: The present disclosure provides a training method for generative adversarial network, which includes: extracting a first-resolution sample image from a second-resolution sample image; separately providing a first input image and a second input image for a generative network to generate a first output image and a second output image respectively, the first input image including a first-resolution sample image and a first noise image, the second input image including the first-resolution sample image and a second noise image; separately providing the first output image and a second-resolution sample image for a discriminative network to output a first discrimination result and a second discrimination result; and adjusting parameters of the generative network to reduce a loss function. The present disclosure further provides an image processing method using the generative adversarial network, a computer device, and a computer-readable storage medium.

Abstract: An image processing method is disclosed. The image processing method may include inputting a first image and a third image to a pre-trained style transfer network model, the third image being a composited image formed by the first image and a second image; extracting content features of the third image and style features of the second image, normalizing the content features of the third image based on the style features of the second image to obtain target image features, and generating a target image based on the target image features and outputting the target image by using the pre-trained style transfer network model.

Abstract: The disclosure relates to an image processing method. The method may include: obtaining an image frame obtained through photographing and performing background separation on the image frame to obtain a subject frame and a background frame; obtaining a plurality of target background frames based on the background frame, in which the plurality of target background frames contain the same background content, and sizes of the background content in the plurality of target background frames are inconsistent; and synthesizing a target subject frame and the plurality of target background frames respectively to obtain a plurality of target image frames, and encoding the plurality of obtained target image frames into a video file, in which the target subject frame is one frame of an image in the subject frame.

Abstract: Provided are a data interaction method and device, a storage medium, and a mobile terminal. The data interaction method is used for a mobile terminal. The mobile terminal includes dual cameras.

Abstract: A cascaded system for classifying an image includes a first cascade layer including a first analysis module coupled to a first input terminal, and a first pooling module coupled to the first analysis module; a second cascade layer including a second analysis module coupled to a second input terminal, and a second pooling module coupled to the first pooling module and the second analysis module; a synthesis layer coupled to the second pooling module, and an activation layer coupled to the synthesis layer.

Abstract: The present disclosure provides a method of training a generative adversarial network. The method includes iteratively enhancing a first noise input in a generative network to generate a first output image; iteratively enhancing a second noise input in the generative network to generate a second output image; transmitting the first output image and a second reference image to a discriminative network, the second reference image corresponding to the first reference image and having a higher resolution than the first reference image; obtaining a first score from the discriminative network based on the second reference image, and a second score from the discriminative network based on the first output image; calculating a loss function of the generative network based on the first score and the second score; and adjusting at least one parameter of the generative network to lower the loss function of the generative network.