Google Inc.

Lytro, Inc.

Nikhil Karnad

Chia-Kai Liang

Kurt Akeley

Kent Oberheu

Garrett Girod

Francis A Benevides

Mike Xiaoli Ma

Yael Pritch Knaan

Derek Pang

Huizhong Chen

Orly Liba

Alex Song

Longqi Cai

Nori Kanazawa

A media application generates training data that includes a first set of visual media items and a second set of visual media items, where the first set of visual media items correspond to the second set of visual items and include distracting objects that are manually segmented. The media application trains a segmentation machine-learning model based on the training data to receive a visual media item with one or more distracting objects and to output a segmentation mask for one or more segmented objects that correspond to the one or more distracting objects.

Segmenting and removing objects from visual media items

A video stream may be captured, and may have a plurality of frames including at least a first frame and a second frame. Each of the frames may have a plurality of views obtained from viewpoints that are offset from each other. A source contour, associated with a source view of the first frame, may be retrieved. Camera parameters, associated with the image capture device used to capture the video stream, may also be retrieved. The camera parameters may include a first offset between the source view and a destination view of the first frame. At least the first offset may be used to project the source contour to the destination view to generate a destination contour associated with the destination view.

Multi-view rotoscope contour propagation

An image such as a light-field image may be processed to provide depth-based blurring. The image may be received in a data store. At an input device, first and second user input may be received to designate a first focus depth and a second focus depth different from the first focus depth, respectively. A processor may identify one or more foreground portions of the image that have one or more foreground portion depths, each of which is less than the first focus depth. The processor may also identify one or more background portions of the image that have one or more background portion depths, each of which is greater than the second focus depth. The processor may also apply blurring to the one or more foreground portions and the one or more background portions to generate a processed image, which may be displayed on a display device.

Depth-based image blurring

A combined video of a scene may be generated for applications such as virtual reality or augmented reality. In one method, a data store may store video data with a first portion having a first importance metric, and a second portion having a second importance metric, denoting that viewing of the first portion is more likely and/or preferential to viewing of the second portion. The subset may be retrieved and used to generate viewpoint video from a virtual viewpoint corresponding to a viewer's viewpoint. The viewpoint video may be displayed on a display device. One of storing the video data, retrieving the subset, and using the subset to generate the viewpoint video may include, based on the difference between the first and second importance metrics, expediting and/or enhancing performance of the step for the first portion, relative to the second portion.

Adaptive control for immersive experience delivery

Growing community of inventors

Mountain View, CA, United States of America

Nikhil Karnad