Google Inc.

Nori Kanazawa

Yael Pritch Knaan

Huizhong Chen

Orly Liba

Nikhil Karnad

Longqi Cai

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.

Growing community of inventors

Mountain View, CA, United States of America

Nori Kanazawa