Google Inc.

Michael Krainin

Ce Liu

Robert J Anderson

Carlos Hernandez Esteban

Changchang Wu

Aaron Joseph Maschinot

Daniel Pettigrew

Michael Rubinstein

Jingyu Cui

Julia Winn

Abraham Stephens

William T Freeman

Steven Maxwell Seitz

Joshua L Weaver

David Robert Gallup

Erik Hubert Dolly Goossens

Dilip Krishnan

Christopher Edward Hoover

Jingbin Wang

Dominik Philemon Kaeser

Mikael Bonnevie

Richard Tucker

Matthew Thomas Valente

Huiwen Chang

Hossein Talebi

David Salesin

Piotr Teterwak

Aaron Yehuda Sarna

Brian Curless

Abhishek Kar

Kyle Sargent

Wenchao Tong

Haifeng Gong

Raanan Sayag

Varun Jampani

Shuchao Bi

Brain L Curless

Dominik Kaeser

William T Frreeman

A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

Single image 3D photography with soft-layering and depth-aware inpainting

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.

Image extension neural networks

Some implementations relate to determining whether glare is present in captured image(s) of an object (e.g., a photo) and/or to determining one or more attributes of any present glare. Some of those implementations further relate to adapting one or more parameters for a glare removal process based on whether the glare is determined to be present and/or based on one or more of the determined attributes of any glare determined to be present. Some additional and/or alternative implementations disclosed herein relate to correcting color of a flash image of an object (e.g., a photo). The flash image is based on one or more images captured by a camera of a client device with a flash component of the client device activated. In various implementations, correcting the color of the flash image is based on a determined color space of an ambient image of the object.

Adaptive glare removal and/or color correction

Systems and methods are described include defining, at a computing device, a set of images based on captured images, projecting, at the computing device, a portion of the set of images from a planar perspective image plane onto a spherical image plane by recasting a plurality of viewing rays associated with the portion of the set of images from a plurality of viewpoints arranged around a curved path to a viewpoint, determining, at the computing device, a periphery boundary corresponding to the viewpoint and generating updated images by removing pixels that are outside of the periphery boundary, and providing, for display, the updated images within the bounds of the periphery boundary.

Omnistereo capture and render of panoramic virtual reality content

Systems and methods are related to a camera rig and generating stereoscopic panoramas from captured images for display in a virtual reality (VR) environment.

Camera rig and stereoscopic image capture

Growing community of inventors

Mountain View, CA, United States of America

Michael Krainin