Google Inc.

David Edward Jacobs

Yael Pritch Knaan

Orly Liba

Kfir Aberman

Marc Stewart Levoy

Jonathan Tilton Barron

Neal Wadhwa

Michael Rubinstein

Rahul Garg

Inbar Mosseri

Huizhong Chen

Junfeng He

Alexander Schiffhauer

Navin Sarma

Longqi Cai

Bryan Feldman

Kai Jochen Kohlhoff

Yossi Gandelsman

Yun-ta Tsai

Xuaner Zhang

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

Systems and methods described herein may relate to potential methods of training a machine learning model to be implemented on a mobile computing device configured to capture, adjust, and/or store image frames. An example method includes supplying a first image frame of a subject in a setting lit within a first lighting environment and supplying a second image frame of the subject lit within a second lighting environment. The method further includes determining a mask. Additionally, the method includes combining the first image frame and the second image frame according to the mask to generate a synthetic image and assigning a score to the synthetic image. The method also includes training a machine learning model based on the assigned score to adjust a captured image based on the synthetic image.

Systems and methods for manipulation of shadows on portrait image frames

Techniques for tuning an image editing operator for reducing a distractor in raw image data are presented herein. The image editing operator can access the raw image data and a mask. The mask can indicate a region of interest associated with the raw image data. The image editing operator can process the raw image data and the mask to generate processed image data. Additionally, a trained saliency model can process at least the processed image data within the region of interest to generate a saliency map that provides saliency values. Moreover, a saliency loss function can compare the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values. Subsequently, the one or more parameter values of the image editing operator can be modified based at least in part on the saliency loss function.

Techniques for reducing a distraction in an image

Techniques for reducing a distractor object in a first image are presented herein. A system can access a mask and the first image. A distractor object in the first image can be inside a region of interest and can have a pixel with an original attribute. Additionally, the system can process, using a machine-learned inpainting model, the first image and the mask to generate an inpainted image. The pixel of the distractor object in the inpainted image can have an inpainted attribute in chromaticity channels. Moreover, the system can determine a palette transform based on a comparison of the first image and the inpainted image. The transform attribute can be different from the inpainted attribute. Furthermore, the system can process the first image to generate a recolorized image. The pixel in the recolorized image can have a recolorized attribute based on the transform attribute of the palette transform.

Techniques for reducing distractions in an image

A camera may capture an image of a scene and use the image to generate a first and a second subpixel image of the scene. The pair of subpixel images may be represented by a first set of subpixels and a second set of subpixels from the image respectively. Each pixel of the image may include two green subpixels that are respectively represented in the first and second subpixel images. The camera may determine a disparity between a portion of the scene as represented by the pair of subpixel images and may estimate a depth map of the scene that indicates a depth of the portion relative to other portions of the scene based on the disparity and a baseline distance between the two green subpixels. A new version of the image may be generated with a focus upon the portion and with the other portions of the scene blurred.

Estimating depth using a single camera

Growing community of inventors

Mountain View, CA, United States of America

David Edward Jacobs