In a learning apparatus, an acquisition unit acquires image data and label data corresponding to the image data. An object candidate extraction unit extracts each object candidate rectangle from the image data. A correct answer data generation unit generates a background object label corresponding to each background object included in each object candidate rectangle as correct answer data corresponding to the object candidate rectangle by using the label data. A prediction unit predicts a classification using each object candidate rectangle and outputs a prediction result. An optimization unit optimizes the object candidate extraction unit and the prediction unit using the prediction result and the correct answer data.

In a learning apparatus, an acquisition unit acquires image data and label data corresponding to the image data. An object candidate extraction unit extracts each object candidate rectangle from the image data. A correct answer data generation unit generates a background object label corresponding to each background object included in each object candidate rectangle as correct answer data corresponding to the object candidate rectangle by using the label data. A prediction unit predicts a classification using each object candidate rectangle and outputs a prediction result. An optimization unit optimizes the object candidate extraction unit and the prediction unit using the prediction result and the correct answer data.

A method for generating one or more 3D models of at least one living object from at least one 2D image comprising the at least one living object. The one or more 3D models can be modified and enhanced. The resulting one or more 3D models can be transformed into at least one 2D display image; the point of view of the output 2D image(s) can be different from that of the input 2D image(s).

A method for generating one or more 3D models of at least one living object from at least one 2D image comprising the at least one living object. The one or more 3D models can be modified and enhanced. The resulting one or more 3D models can be transformed into at least one 2D display image; the point of view of the output 2D image(s) can be different from that of the input 2D image(s).

In various embodiments, a device receives a first video stream of a video conference. The device receives a second video stream of the video conference. The second video stream includes an indicated location for video of the second video stream relative to video of the first video stream. The device merges the first video stream and the second video stream into an overlapped video having the video of the second video stream located at the indicated location relative to the video of the first video stream. The device provides the overlapped video for display.

In various embodiments, a device receives a first video stream of a video conference. The device receives a second video stream of the video conference. The second video stream includes an indicated location for video of the second video stream relative to video of the first video stream. The device merges the first video stream and the second video stream into an overlapped video having the video of the second video stream located at the indicated location relative to the video of the first video stream. The device provides the overlapped video for display.

A method for generating virtual pseudo three dimensional 360 degree outputs from 2D images of an object 102 is provided. An image viewer plane of the object 102 in the 3D image to be rendered on a user device 108 is detected using an augmented reality technique. An image viewer plane is placed facing the user device 108 rendering ‘Image 0’ and movement coordinates of the user device 108 with respect to the image viewer plane is detected to calculate the virtual pseudo 3D image set to be displayed based on at least one angle of view by performing interpolation between two consecutive virtual pseudo 3D images. The image viewer plane is changed with respect to the movement of the user device 108 to change the virtual pseudo 3D image and the interpolated virtual pseudo 3D image on the plane and that image is displayed as an augmented reality object in real-time to the user device 108.

A method for generating virtual pseudo three dimensional 360 degree outputs from 2D images of an object 102 is provided. An image viewer plane of the object 102 in the 3D image to be rendered on a user device 108 is detected using an augmented reality technique. An image viewer plane is placed facing the user device 108 rendering ‘Image 0’ and movement coordinates of the user device 108 with respect to the image viewer plane is detected to calculate the virtual pseudo 3D image set to be displayed based on at least one angle of view by performing interpolation between two consecutive virtual pseudo 3D images. The image viewer plane is changed with respect to the movement of the user device 108 to change the virtual pseudo 3D image and the interpolated virtual pseudo 3D image on the plane and that image is displayed as an augmented reality object in real-time to the user device 108.

An apparatus comprising an interface, a structured light projector and a processor. The interface may receive pixel data. The structured light projector may generate a structured light pattern. The processor may process the pixel data arranged as video frames, perform operations using a convolutional neural network to determine a binarization result and an offset value and generate disparity and depth maps in response to the video frames, the structured light pattern, the binarization result, the offset value and a removal of error points. The convolutional neural network may perform a partial block summation to generate a convolution result, compare the convolution result to a speckle value to determine the offset value, generate an adaptive result in response to performing a convolution operation, compare the video frames to the adaptive result to generate the binarization result for the video frames, and remove the error points from the binarization result.

An apparatus comprising an interface, a structured light projector and a processor. The interface may receive pixel data. The structured light projector may generate a structured light pattern. The processor may process the pixel data arranged as video frames, perform operations using a convolutional neural network to determine a binarization result and an offset value and generate disparity and depth maps in response to the video frames, the structured light pattern, the binarization result, the offset value and a removal of error points. The convolutional neural network may perform a partial block summation to generate a convolution result, compare the convolution result to a speckle value to determine the offset value, generate an adaptive result in response to performing a convolution operation, compare the video frames to the adaptive result to generate the binarization result for the video frames, and remove the error points from the binarization result.