Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.

In one embodiment, a computing device determines a window of time that is available after each operation to fill a frame buffer. The device determines a first number indicating a number of elements of a requested content that fit into a display region, an increment based on an application-specific rule, and a second number indicating a number of elements to pre-generate based on the first number and the increment. The device selects one or more pre-generation tasks for pre-generating content for the second number of select elements of the requested content. During the window of time, the device executes at least a subset of the pre-generation tasks to pre-generate content for a corresponding subset of the select elements. The pre-generated subset of the select elements is stored in an application-tailored recycler.

An apparatus and method are described for a non-uniform rasterizer. For example, one embodiment of an apparatus comprises: a graphics processor to process graphics data and render images using the graphics data; and a non-uniform rasterizer within the graphics processor to determine different resolutions to be used for different regions of an image, the non-uniform rasterizer to receive a plurality of polygons to be rasterized and to responsively rasterize the polygons in accordance with the different resolutions.

A method and apparatus for loading an image, where the method includes acquiring a viewport size of a target apparatus, and a scale of an image displayed on the target apparatus with respect to an original size of the image; in a predetermined image set to be displayed, determining, an image to be displayed matching the viewport size and the scale, as a target image to be displayed; and loading the target image to be displayed.

A graphical user interface (GUI) includes an image list associated with a display component of a display device. The image list has an index of logical images, where each of the logical images has a fixed pixel size. The GUI further includes an image container connected to the image list, where the image container comprises a plurality of different size versions of at least some of the logical images. The GUI further includes one or more control objects, where each of the control objects is configured to draw a corresponding image from the index of logical images of the image list. The GUI is configured to update the index of logical images of the image list with the different size versions sourced from the image container in response to a scale change of the display component.

Aspects of the subject disclosure may include, for example, obtaining image content over a communication network, determining a predicted viewpoint of a user associated with the image content, and adjusting the image content to equirectangular image content according to the predicted viewpoint. Further aspects can include downscaling the equirectangular image content according to a display capability of a mobile device resulting in a downscaled equirectangular image content, cropping the downscaled equirectangular image content resulting in a cropped equirectangular image content, and providing, over the communication network, the cropped equirectangular image content to the mobile device. Other embodiments are disclosed.

Systems and methods for screen sharing are provided. The screen sharing may comprise providing image data from a sender system to a receiver system. The receiver system may be a Virtual Reality [VR] system configured to render the image data in a virtual environment by projecting the image data onto a virtual canvas. At the sender system, visual content may be identified which is to be shared with the receiver system. The rendering or display of the virtual environment by the receiver may impose legibility constraints on the visual content. Accordingly, an adjusted version of the visual content may be generated which provides improved legibility when viewed in the virtual environment. The image data representing the adjusted version of the visual content may then be provided to the receiver system. Accordingly, the legibility of the visual content shared by the sender system may be improved when rendered, displayed and subsequently viewed by a user in the virtual environment

A method for dynamic scaling is disclosed. The method includes identifying first scene information to be rendered for display on an electronic device, the electronic device including a screen with a physical resolution, the first scene information associated with an application. The method also includes generating a scaling factor, the scaling factor controlling a resolution of the first scene information as rendered on the screen independently of the physical resolution of the screen. Additionally, the method includes rendering the first scene information as one or more pixels of a virtual display with a virtual resolution based on the scaling factor.

Artistic styles extracted from source images may be applied to target images to generate stylized images and/or video sequences. The extracted artistic styles may be stored as a plurality of layers in one or more neural networks, which neural networks may be further optimized, e.g., via the fusion of various elements of the networks' architectures. The artistic style may be applied to the target images and/or video sequences using various optimization methods, such as the use of a first version of the neural network by a first processing device at a first resolution to generate one or more sets of parameters (e.g., scaling and/or biasing parameters), which parameters may then be mapped for use by a second version of the neural network by a second processing device at a second resolution. Analogous multi-processing device and/or multi-network solutions may also be applied to other complex image processing tasks for increased efficiency.

An image authentication method is provided. An original image is divided into blocks. An interpolation algorithm is performed on each block so as to obtain a first image. Each pixel in the first image is mapped into an index based on a palette compression technique, so as to generate a second image. Each index is divided into multiple secret values, and a secret sharing algorithm is performed based on the secret values to obtain multiple partial shares. A transparent map is generated according to the partial shares, and a lossless image filed is generated by combining the original image with the transparent map.