Abstract: A method for developing an enhancement model for low-quality visual data, the method comprising the steps of receiving one or more sections of higher-quality visual data; and training a hierarchical algorithm. The hierarchical algorithm is operable to increase the quality of one or more sections of lower-quality visual data so as to substantially reproduce the one or more sections of higher-quality visual data. The hierarchical algorithm is then outputted.

Abstract: An example system includes a processor and a memory. The system performs sub-pixel convolution that is free of checkerboard artifacts. In one example implementation, the system may execute a method that includes initializing one or more parameters of a sub-kernel of a kernel and copying the one or more parameters of the sub-kernel to other sub-kernels of the kernel. The method may further include performing convolution of an input image with the sub-kernels of the kernel and generating a plurality of first output images. A second output image is then generated based on the plurality of first output images.

Abstract: A method includes selecting two or more frames from a plurality of frames of a video, downscaling the two or more frames, estimating a flow data based on an optical flow associated with the downscaled two or more frames, upscaling the flow data, generating a refined flow data based on the upscaled flow data and the downscaled two or more frames, upscaling the refined flow data, and synthesizing an image based on the upscaled refined flow data and the two or more frames.

Abstract: A neural network is trained to process received visual data to estimate a high-resolution version of the visual data using a training dataset and reference dataset. A set of training data is generated, and a generator convolutional neural network parameterized by first weights and biases is trained by comparing characteristics of the training data to characteristics of the reference dataset. The first network is trained to generate super-resolved image data from low-resolution image data and the training includes modifying first weights and biases to optimize processed visual data based on the comparison between the characteristics of the training data and the characteristics of the reference dataset.

Abstract: A neural network is trained to process received visual data to estimate a high-resolution version of the visual data using a training dataset and reference dataset. A set of training data is generated and a generator convolutional neural network parameterized by first weights and biases is trained by comparing characteristics of the training data to characteristics of the reference dataset. The first network is trained to generate super-resolved image data from low-resolution image data and the training includes modifying first weights and biases to optimize processed visual data based on the comparison between the characteristics of the training data and the characteristics of the reference dataset.

Abstract: A method for increasing the quality of a section of visual data communicated over a network from a first node to a second node, the method at the second node including receiving a lower-quality visual data via a network, receiving a corresponding reference to an algorithm operable to increase a quality of the lower-quality visual data, the algorithm selected based on a higher-quality visual data from which the lower-quality visual data was generated, and using the algorithm to increase the quality of the lower-quality visual data to recreate the higher-quality visual data.

Abstract: A method for enhancing one or more sections of lower-quality visual data using a hierarchical algorithm, the method comprising receiving one or more sections of lower-quality visual data. The one or more sections of lower-quality visual data are enhanced to one or more sections of higher-quality visual data using the hierarchical algorithm. Additionally, at least the first step of the hierarchical algorithm is performed in a lower-quality domain; and wherein the hierarchical algorithm operates in both a higher-quality domain and the lower-quality domain.

Abstract: A method includes selecting a plurality of low-resolution frames associated with a video, performing a first motion estimation between a first frame and a second frame, performing a second motion estimation between a third frame and the second frame, generating a high-resolution frame representing the second frame based on the first motion estimation, the second motion estimation and the second frame using a sub-pixel convolutional neural network.

Abstract: A method for training an algorithm to process at least a section of received visual data using a training dataset and reference dataset. The method comprises an iterative method with iterations comprising: generating a set of training data using the algorithm; comparing one or more characteristics of the training data to one or more characteristics of at least a section of the reference dataset; and modifying one or more parameters of the algorithm to optimise processed visual data based on the comparison between the characteristic of the training data and the characteristic of the reference dataset. The algorithm may output the processed visual data with the same content as the at least a section of received visual data. Some aspects and/or implementations provide for improved super-resolution of lower quality images to produce super-resolution images with improved characteristics (e.g. less blur, less undesired smoothing) compared to other super-resolution techniques.

Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method including receiving at least a plurality of neighbouring sections of lower-quality visual data. A plurality of input sections from the received plurality of neighbouring sections of lower quality visual data are selected and features are extracted from those plurality of input sections of lower-quality visual data. A target section based on the extracted features from the plurality of input sections of lower-quality visual data is then enhanced.

Abstract: A system (e.g., an auto-encoder system) includes an encoder, a decoder and a learning module. The encoder generates compressed video data using a lossy compression algorithm, the lossy compression algorithm being implemented using a trained neural network with at least one convolution, generate at least one first parameter based on the compressed video data, and communicate the compressed video data and the model to at least one device configured to decode the compressed video data using an inverse algorithm based on the lossy compression algorithm. The decoder generates decoded video data based on the compressed video data using the inverse algorithm and the model, and generate at least one second parameter based on the decoded video data. The learning module trains the model using the at least one first parameter and the at least one second parameter.

Abstract: A method for enhancing lower-quality visual data using hierarchical algorithms, the method comprising the steps of: receiving one or more sections of lower-quality visual data; applying a hierarchical algorithm to the one or more sections of lower-quality visual data to enhance the one or more sections of lower-quality visual data to one or more sections of higher-quality visual data, wherein the hierarchical algorithm was developed using a learned approach; and outputting the one or more sections of higher-quality visual data.

Abstract: Embodiments of the present invention provide for hiding information in an image. A first pixel point and a second pixel point that are adjacent in an image are extracted. A first sub-pixel of the first pixel point and a second sub-pixel of the second pixel point that are to be combined during display on a display device are determined, wherein the display device determines a combined pixel value according to pixel values of the first sub-pixel and the second sub-pixel in a predefined manner. Information is hidden using parity properties of a sum of pixel values of the first sub-pixel and the second sub-pixel while the combined pixel value determined according to pixel values of the first sub-pixel and the second sub-pixel in the predefined manner is kept unchanged. By using unique display characteristics of a display device, information is hidden in an image without changing display effect of the image on the display device.

Abstract: Systems and methods for emoji prediction and visual sentiment analysis are provided. An example system includes a computer-implemented method. The method may be used to predict emoji or analyze sentiment for an input image. An example method includes the step of receiving an image. The example method further includes the steps of generating an emoji embedding for the image and generating a sentiment label for the image using the emoji embedding. The emoji embedding may be generated using a machine learning model.

Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method comprises receiving at least one section of lower-quality visual data; and extracting a subset of features, from the at least one section of lower-quality visual data. A plurality of layers of reduced-dimension visual data from the extracted features are formed and enhanced to form at least one section of higher-quality visual data. The at least one section of higher-quality visual data corresponds to the at least one section of lower-quality visual data received.

Abstract: Systems and methods generate a face-swapped image from a target image using a convolutional neural network trained to apply a source identity to the expression and pose of the target image. The convolutional neural network produces face-swapped images fast enough to transform a video stream. An example method includes aligning the face portion of a target image from an original view to a reference view to generate a target face and generating a swapped face by changing the target face to that of a source identity using a convolutional neural network trained to minimize loss of content from the target face and style from the source identity. The method also includes realigning the swapped face from the reference view to the original view and generating a swapped image by stitching the realigned swapped face with the remaining portion of the target image.

Abstract: A method for enhancing at least a section of lower-quality visual data using a hierarchical algorithm, the method comprising receiving at least a plurality of neighbouring sections of lower-quality visual data. A plurality of input sections from the received plurality of neighbouring sections of lower quality visual data are selected and features are extracted from those plurality of input sections of lower-quality visual data. A target section based on the extracted features from the plurality of input sections of lower-quality visual data is then enhanced.

Abstract: A method for enhancing at least a section of lower-quality visual data, the method comprising at least a section of the lower-quality visual data being received. A hierarchical algorithm is then selected from a plurality of hierarchical algorithms, wherein the step of selection is based on a predetermined metric and wherein the hierarchical algorithms were developed using a learned approach and at least one of the hierarchical algorithms is operable to increase the quality of the lower-quality visual data. The selected hierarchical algorithm is then used to increase the quality of the lower-quality visual data to create a higher-quality visual data.

Abstract: A method for training learned hierarchical algorithms, the method comprising the steps of receiving input data and generating metrics from the input data. At least one hierarchical algorithm is then selected from a plurality of predetermined hierarchical algorithms based on comparing the generated metrics from the input data and like metrics for each of the plurality of predetermined hierarchical algorithms. The selected hierarchical algorithm is developed based on the input data and the developed hierarchical algorithm is outputted.

Abstract: A method for enhancing visual data when communicating visual data over a network from a first node to a second node. The method at the first node comprises developing at least one modified hierarchical algorithm from a known hierarchical algorithm operable to substantially recreate at least one section of higher-quality visual data. References to one or more known hierarchical algorithms from which the modified hierarchical algorithms were developed are transmitted to the second node along with one or more modifications to the one or more known hierarchical algorithms operable to reproduce the one or more modified hierarchical algorithms from the known hierarchical algorithms. The second node is able to recreate substantially the higher-quality video using the modified hierarchical algorithm.