There is described a deep learning supervised regression based model including methods and systems for facial attribute prediction and use thereof. An example of use is an augmented and/or virtual reality interface to provide a modified image responsive to facial attribute predictions determined from the image. Facial effects matching facial attributes are selected to be applied in the interface

A liveness detection method includes: controlling a display screen to display a color according to a predetermined color display sequence, the color display sequence including at least two different colors; capturing an image of a target object in a color display process of the display screen; acquiring a color change sequence of a face of the target object in the image over time; and determining whether the target object is live based on a matching relationship between the color display sequence and the color change sequence.

Methods, devices, apparatuses, and systems for living body detection are provided. In one aspect, a living body detection method includes: determining multiple target face images from an acquired to-be-detected video based on similarities between multiple face images included in the to-be-detected video, and determining a living body detection result for the to-be-detected video based on the multiple target face images.

Techniques are provided for generating one or more three-dimensional (3D) models. In one example, an image of an object (e.g., a face or other object) is obtained, and a 3D model of the object in the image is generated. The 3D model includes geometry information. Color information for the 3D model is determined, and a fitted 3D model of the object is generated based on a modification of the geometry information and the color information for the 3D model. In some cases, the color information (e.g., determination and/or modification of the color information) and the fitted 3D model can be based on one or more vertex-level fitting processes. A refined 3D model of the object is generated based on the fitted 3D model and depth information associated with the fitted 3D model. In some cases, the refined 3D model can be based on a pixel-level refinement or fitting process.

A change in a state of a user is more properly recognized by the user. A notification device includes a physical condition information acquiring section or a makeup information acquiring section, a light emitting section and a display section serving as a notifying section, a control section, and a determining section. The physical condition information acquiring section or the makeup information acquiring section acquires face information. The light emitting section and the display section serving as the notifying section perform a notification on the basis of the face information. The determining section determines a change between the face information before the notification and the face information after the notification. The control section controls the notification by the light emitting section and the display section serving as the notifying section on the basis of a determination result by the determining section.

Implementations described herein relate to methods, systems, and computer-readable media to render a foreground video. In some implementations, a method includes receiving a plurality of video frames that include depth data and color data. The method further includes downsampling the frames of the video. The method further includes, for each frame, generating an initial segmentation mask that categorizes each pixel of the frame as foreground pixel or background pixel. The method further includes determining a trimap that classifies each pixel of the frame as known background, known foreground, or unknown. The method further includes, for each pixel that is classified as unknown, calculating and storing a weight in a weight map. The method further includes performing fine segmentation to obtain a binary mask for each frame. The method further includes upsampling the plurality of frames based on the binary mask for each frame to obtain a foreground video.

Techniques for face tracking in a telemedicine environment. A method of face tracking in a telemedicine environment may include streaming video data to a user device from an agent device via an application on the agent device, the video data captured by a camera connected to the agent device through a first connector, analyzing a frame of the video data by an extension of the application to determine a position of a provider's face in the video data, generating, by the extension, a movement instruction based at least on the position of the provider's face in the video data, sending, by the extension, the movement instruction to a base application in communication with a motorized camera base coupled to the agent device through a second connector, wherein the motorized camera base executes the movement instruction causing a change in an orientation of the camera.

A system and a method for face recognition are disclosed. The system also includes an image capturing subsystem configured to capture one or more images of faces. The system also includes a feature extraction subsystem configured to extract one or more features from the one or more images of faces. The system also includes a feature comparison subsystem configured to compare the one or more extracted features in a local database. The system also includes a feature transmission subsystem configured to transmit the one or more images and one or more extracted features to a remote server. The feature transmission subsystem is also configured to compare the one or more transmitted features to the one or more features pre-stored in the remote server. The system also includes a feature regeneration subsystem configured to regenerate the one or more matched features in the local database from the remote server.

A system includes an image sensor having a plurality of pixels that form a plurality of regions of interest (ROIs), and configured to operate at a frame rate higher than a threshold rate. The system also includes an image processing resource. The system further includes control circuitry configured to perform operations that include obtaining, from the image sensor, a full-resolution image of an environment. The full-resolution image contains each respective ROI of the plurality of ROIs. The operations also include selecting a particular ROI based on the full-resolution image, and detecting an object of interest in the particular ROI. The operations include determining a mode of operation by which subsequent image data generated by the particular ROI is to be processed. The operations further include processing, based on the mode of operation and the frame rate, the image data comprising a plurality of ROI images of the object of interest.

An apparatus and a method are provided that are used to generate a three-dimensional model in which a more natural texture is set for an occlusion region of which a texture is not obtained from a two-dimensional image. A three-dimensional shape restoring section that generates a three-dimensional model on the basis of a two-dimensional image, and a texture processor that attaches a texture to the three-dimensional model are included. The texture processor acquires, from a DB, an existing texture similar to a texture acquired from the two-dimensional image, calculates a conversion function that is used so that the existing texture has a color closer to the color of the acquired texture, and sets, for a region of which a texture is not acquired from the two-dimensional image, a texture calculated by applying the conversion function to the existing texture. For example, a texture calculated by applying the conversion function is set for an occlusion region of which a texture is not obtained from a two-dimensional image.