Abstract: A system and method implement deep learning on a mobile device to provide a convolutional neural network (CNN) for real time processing of video, for example, to color hair. Images are processed using the CNN to define a respective hair matte of hair pixels. The respective object mattes may be used to determine which pixels to adjust when adjusting pixel values such as to change color, lighting, texture, etc. The CNN may comprise a (pre-trained) network for image classification adapted to produce the segmentation mask. The CNN may be trained for image segmentation (e.g. using coarse segmentation data) to minimize a mask-image gradient consistency loss. The CNN may further use skip connections between corresponding layers of an encoder stage and a decoder stage where shallower layers in the encoder, which contain high-res but weak features are combined with low resolution but powerful features from deeper decoder layers.

Abstract: Identifying a state of a user (e.g., attentive, distracted, mind wandering, etc.) based on the user's physiological (e.g., pupillary) response to luminance change events in which a portion or all of the content quickly becomes brighter or dimmer.

Abstract: Unmanned vehicles can be terrestrial, aerial, nautical, or multi-mode. Unmanned vehicles may be used to survey a property in response to or in anticipation of a security threat or damage to the property. For example, an unmanned vehicle may analyze information about the property and based on the information provide graphics and information associated with the surveying of the property.

Abstract: An image transmission apparatus, an image transmission method, and a program enable a transmission destination to display an image similar to the image displayed at a transmission source. A display target image generation section generates a display target image having a display non-target region reflecting settings of a safe area of a display section. A display control section causes the display section to display an actual display image constituting a portion of the display target image. A transmission image generation section generates a transmission image that represents a portion of the display target image and excludes at least a portion of the display non-target region. A transmission section transmits the transmission image.

Abstract: According to various implementations, a method is performed at an electronic device including one or more processors, non-transitory memory, and one or more displays. The method includes, while presenting a virtual environment, via the one or more displays, obtaining a request for interaction from an external source. The virtual environment includes a first plurality of available presentation regions and a second plurality of unavailable presentation regions. The method includes determining whether the request for interaction from the external source satisfies one or more interaction criteria. The method includes presenting, via the one or more displays, an avatar associated with the external source at one of the first plurality of available presentation regions within the virtual environment, in response to determining that the external source satisfies the one or more interaction criteria.

Abstract: Methods and a system for pixel-by-pixel correction of diffuse reflected and specular reflected light on a display device of an information handling system. Voltage values of pixels of the display device are measured by sensors. Measured voltage values of a pixel are converted to a digital value. A digital correction value calculated based on whether diffuse reflected light or diffuse reflected light and specular reflected light is found on the pixel. A sigmoid transfer function and discrete sharpening filter is performed on the pixel, if the digital correction value is less than zero.

Abstract: A method and system for cost effective, convenient remote color reproduction and matching that can be used to convey color to observers remote to the physical source of color. Such remote observers can include product consumers wishing to view a product color, for example. In a preferred embodiment, the method comprises capture of article or product reflectance spectra and the use of this spectrum to filter ambient light or directed light in the environment of a remote user. Other embodiments of methods include various techniques to capture product spectral information and color matching functions useful for color reproduction using colored light sources. Additional systems embodiments include devices exploiting multiprimary displays to render the product color in avoidance of metamerism.

Abstract: A light-emitting apparatus comprising pixels that each includes a light-emitting element and a drive transistor for supplying a current according to a luminance signal to the light-emitting element and a signal supply circuit supplying the luminance signal to the drive transistor. The apparatus operates display modes including a first display mode and a second display mode in which a maximum luminance is higher than in the first display mode. The signal supply circuit, in a case where the display data has a maximum luminance value, supplies to the drive transistor, as the luminance signal, different voltages in the first and second display modes, and in a case where the display data has a minimum luminance value, supplies to the drive transistor, as the luminance signal, different voltages in the first and second display modes.

Abstract: A virtual image generation method and apparatus, an electronic device and a storage medium which relates to the field of artificial intelligence technologies such as augmented reality, computer vision and deep learning. A specific implementation scheme involves: acquiring base coefficients corresponding to key points of a target face based on a target face picture; generating a structure of a virtual image of the target face based on a mapping relationship of spatial alignment between a preset virtual model and a standard model, a base of the standard model and the base coefficients corresponding to the key points of the target face; and performing texture filling on the structure of the virtual image based on textures of the target face picture, to obtain the virtual image of the target face.

Abstract: A system and method for monitoring performance of an industrial process includes an input port for receiving signals representative of one or more performance parameters generated by the industrial process, a user interface including a display and a controller that is operably coupled with the input port and the user interface. The controller is configured to repeatedly receive signals over time via the input port representative of the one or more performance parameters of the industrial process and to generate a plurality of snapshots, wherein each snapshot includes a graphical representation of the one or more performance parameters of the industrial process at a corresponding time. The controller is configured to generate an animatable heat map including two or more of the plurality of snapshots arranged temporally and to display the animatable heat map on the display.

Abstract: A perceived gamut (PG) of a physical display device presenting frames of an image sequence to a human viewer may be increased. An interface of the system receives a sequence of frames from an image sequence source with each frame having input color data associated with each pixel of the respective frame, the input color data being given in a specified color space. A perceived color computation module computes for each particular frame of the received image sequence perceived colors of each pixel and a frame-specific adapted white point. An optimizer module applies a chromatic adaptation transformation to each window frame to determine display gamut adjusted perceived colors of each pixel of the respective frame and an error per window frame. The chromatic adaptation transformation is updated for all window frames to minimize the determined error, and the current frame is output to the display.

Abstract: An information processing apparatus includes: a processor; an image processor to produce an image data for being displayed on a display; and a memory to store a screen data, the screen data being capable of being transferred from the memory to the image processor at a higher transfer rate and a lower transfer rate; wherein, when a new screen data is transferred from the memory to the image processor, the processor sets the lower transfer rate during an interval at which the image processor switches the image data from an old image data to a new image data.

Abstract: Techniques for face tracking comprise receiving landmark data associated with a plurality of images indicative of at least one facial part. Representative images corresponding to the plurality of images may be generated based on the landmark data. Each representative image may depict a plurality of segments, and each segment may correspond to a region of the at least one facial part. The plurality of images and corresponding representative images may be input into a neural network to train the neural network to predict a feature associated with a subsequently received image comprising a face. An animation associated with a facial expression may be controlled based on output from the trained neural network.

Abstract: A method for determining human eye close degrees includes: acquiring a face image; determining a human eye open amplitude and a reference distance in the face image; calculating a relative amplitude of the human eye open amplitude relative to the reference distance; acquiring a maximum relative amplitude; and calculating a human eye close weight in the face image based on the relative amplitude and the maximum relative amplitude, the human eye close weight being configured to measure a human eye close degree.

Abstract: Systems, apparatus, and methods for reducing display latency. An application may present a rendered frame multiple times successively, within the time period of display for the current frame. The rendered frame is presented again without the application re-rendering the scene. The application may resubmit previously rendered frames in a GPU pipeline such that a compositor software may sample, process, and display a most recent frame, creating more apparent responsiveness in a composited application to user inputs.

Abstract: Some embodiments involve a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.

Abstract: The display method includes obtaining a target image showing a target region including a surface, displaying a simulation image on a display, the simulation image being obtained by superimposing a display image on the target image, the display image corresponding to an image to be projected by a projector on the surface, displaying the target image included in the simulation image on the display with a brightness based on first information which specifies a brightness of the target region, and displaying the display image included in the simulation image on the display with a brightness based on second information which specifies a brightness of the display image.

Abstract: A method for generating an image with uniform brightness, the method includes: providing a first sub-image having a first overlapping portion and a first non-overlapping portion; providing a second sub-image having a second overlapping portion and a second non-overlapping portion; and superimposing the first sub-image with the second sub-image through the first overlapping portion and the second overlapping portion. The brightness of the first overlapping portion of the first sub-image is complementary to the brightness of the second overlapping portion of the second sub-image.

Abstract: A luminescence shock avoidance algorithm selectively limits the brightness level of a display device when the display device is activated in a dark environment to prevent the temporary vision impairment that can occur when a display device is activated in a dark environment. The algorithm receives the state of the display (e.g. on or in standby mode), and can optionally receive an ambient lighting value from an ambient light sensor and a user-selectable manual brightness adjustment setting to determine whether luminescence shock avoidance should even be triggered, and if it is triggered, how much should the brightness level of the display be limited.

Abstract: A system for updating an image on a display device includes pixels in a pixel array. The system includes a display subsystem for executing commands and displaying images, the display subsystem also includes a parser for receiving image frame data, and extracting updated image data and commands. A storage device is used for storing the updated image data in an updated cache location according to the commands. A loader is used for reading the commands to identify and fetch the updated image data from the storage device. Display backplane circuitry is used for receiving the updated image data from the loader and for updating pixel driver circuity for pixels within the updated image data. The examples described are ideal for driving micro-displays such as LCoS micro-LED displays.