Abstract: Aspects of the disclosure relate to using machine learning for foreground mask estimation. A computing platform may receive a set of images and corresponding ground truth foreground masks. Using the set of images and the corresponding ground truth foreground masks, the computing platform may train the first neural network to distinguish between image foregrounds and backgrounds, which may result in a first set of foreground masks. For each image and based on a corresponding foreground mask, the computing platform may estimate a first background clean plate. Using the set of images, the first background clean plates, and a set of corresponding ground truth mask images, the computing platform may train a second neural network, which may configure the second neural network to output foreground masks based on video input information. The computing platform may deploy, to an implementation computing device, the second neural network.

Abstract: Aspects of the disclosure relate to using machine learning for foreground mask estimation. A computing platform may receive a set of images and corresponding ground truth foreground masks. Using the set of images and the corresponding ground truth foreground masks, the computing platform may train the first neural network to distinguish between image foregrounds and backgrounds, which may result in a first set of foreground masks. For each image and based on a corresponding foreground mask, the computing platform may estimate a first background clean plate. Using the set of images, the first background clean plates, and a set of corresponding ground truth mask images, the computing platform may train a second neural network, which may configure the second neural network to output foreground masks based on video input information. The computing platform may deploy, to an implementation computing device, the second neural network.

Abstract: A system for enhancing a depth map associated with a 2D image wherein a face detector analyzes the 2D image to determine a position of a face in the 2D image, the system utilizes the position to derive a depth model; and the depth model is combined with the depth map to generate an enhanced depth map.

Abstract: A depth estimation and conversion apparatus and method is provided. Depth of an video may be estimated by extracting feature information from the input video, and estimating the depth of the input video based on the extracted feature information.

Abstract: A system for enhancing a depth map associated with a 2D image wherein a face detector analyzes the 2D image to determine a position of a face in the 2D image, the system utilizes the position to derive a depth model; and the depth model is combined with the depth map to generate an enhanced depth map.

Abstract: A method of determining a configuration of stereoscopic rendering parameters in a computer graphics environment by periodically determining the location of data within the viewing frustum and adapting the parameters to generate a stereo render.

Abstract: A method of generating images suitable for use with a multi-view stereoscopic display including the steps of intercepting data passed from an application to an application programming interface, the data representing a scene or object to be displayed on the display; processing the data to render multiple views of the scene or object; creating modified data by modifying the intercepted data to represent the multiple views; and passing the modified data to the application programming interface.