Google Inc.

Bryan Feldman

Daniel Joseph Filip

David C Lee

Scott Ettinger

Evan Rapoport

Mikkel Crone Köser

Yael Pritch Knaan

Huizhong Chen

Orly Liba

David Edward Jacobs

Jacob Mintz

Alexander Schiffhauer

Navin Sarma

Longqi Cai

Jake Mintz

Siyang Li

A media application receives user input that indicates one or more objects to be erased from a media item. The media application translates the user input to a bounding box. The media application provides a crop of the media item based on the bounding box to a segmentation machine-learning model. The segmentation machine-learning model outputs a segmentation mask for one or more segmented objects in the crop of the media item and a corresponding segmentation score that indicates a quality of the segmentation mask.

Performing segmentation of objects in media items based on user input

A method and system is disclosed for simulating different types of camera lens on a device by guiding a user through a set of images to be captured in connection with one or more desired lens effects. In one aspect, a wide-angle lens may be simulated by taking a plurality of images that have been taken at a particular location over a set of camera orientations that are determined based on the selection of the wide-angle lens. The mobile device may provide prompts to the user indicating the camera orientations for which images should be captured in order to generate the simulated camera lens effect.

Synthetic camera lenses

Growing community of inventors

Mountain View, CA, United States of America

Bryan Feldman