Google Inc.

Jiawen Chen

Marc Stewart Levoy

Jonathan Tilton Barron

Rahul Garg

Tianfan Xue

Neal Wadhwa

Samuel William Hasinoff

Changyin Zhou

Jian Jim Wang

Roman Lewkow

Yael Pritch Knaan

Sameer Ansari

Yicheng Wu

Michael Gharbi

Pratul Preeti Srinivasan

Qiurui He

Jian Wang

Shumian Xin

A method includes obtaining an input image that contains a particular representation of lens flare, and processing the input image by a machine learning model to generate a de-flared image that includes the input image with at least part of the particular representation of lens flare removed. The machine learning (ML) model may be trained by generating training images that combine respective baseline images with corresponding lens flare images. For each respective training image, a modified image may be determined by processing the respective training image by the ML model, and a loss value may be determined based on a loss function comparing the modified image to a corresponding baseline image used to generate the respective training image. Parameters of the ML model may be adjusted based on the loss value determined for each respective training image and the loss function.

Learning-based lens flare removal

A method includes obtaining dual-pixel image data that includes a first sub-image and a second sub-image, and generating an in-focus image, a first kernel corresponding to the first sub-image, and a second kernel corresponding to the second sub-image. A loss value may be determined using a loss function that determines a difference between (i) a convolution of the first sub-image with the second kernel and (ii) a convolution of the second sub-image with the first kernel, and/or a sum of (i) a difference between the first sub-image and a convolution of the in-focus image with the first kernel and (ii) a difference between the second sub-image and a convolution of the in-focus image with the second kernel. Based on the loss value and the loss function, the in-focus image, the first kernel, and/or the second kernel, may be updated and displayed.

Defocus blur removal and depth estimation using dual-pixel image data

Apparatus and methods related to using machine learning to determine depth maps for dual pixel images of objects are provided. A computing device can receive a dual pixel image of at least a foreground object. The dual pixel image can include a plurality of dual pixels. A dual pixel of the plurality of dual pixels can include a left-side pixel and a right-side pixel that both represent light incident on a single dual pixel element used to capture the dual pixel image. The computing device can be used to train a machine learning system to determine a depth map associated with the dual pixel image. The computing device can provide the trained machine learning system.

Depth prediction from dual pixel images

Scenes can be imaged under low-light conditions using flash photography. However, the flash can be irritating to individuals being photographed, especially when those individuals' eyes have adapted to the dark. Additionally, portions of images generated using a flash can appear washed-out or otherwise negatively affected by the flash. These issues can be addressed by using a flash at an invisible wavelength, e.g., an infrared and/or ultraviolet flash. At the same time a scene is being imaged, at the invisible wavelength of the invisible flash, the scene can also be imaged at visible wavelengths. This can include simultaneously using both a standard RGB camera and a modified visible-plus-invisible-wavelengths camera (e.g., an 'IR-G-UV' camera). The visible and invisible image data can then be combined to generate an improved visible-light image of the scene, e.g., that approximates a visible light image of the scene, had the scene been illuminated during daytime light conditions.

Dark flash photography with a stereo camera

Imaging systems can often gather higher quality information about a field of view than the unaided human eye. For example, telescopes may magnify very distant objects, microscopes may magnify very small objects, and high frame-rate cameras may capture fast motion. The present disclosure includes devices and methods that provide real-time vision enhancement without the delay of replaying from storage media. The disclosed devices and methods may include a live view user interface with two or more interactive features or effects that may be controllable in real-time. Specifically, the disclosed devices and methods may include a live view display and image and other information enhancements, which utilize in-line computation and constant control.

Graphic interface for real-time vision enhancement

Systems and methods described herein may relate to image transformation utilizing a plurality of deep neural networks. An example method includes receiving, at a mobile device, a plurality of image processing parameters. The method also includes causing an image sensor of the mobile device to capture an initial image and receiving, at a coefficient prediction neural network at the mobile device, an input image based on the initial image. The method further includes determining, using the coefficient prediction neural network, an image transformation model based on the input image and at least a portion of the plurality of image processing parameters. The method additionally includes receiving, at a rendering neural network at the mobile device, the initial image and the image transformation model. Yet further, the method includes generating, by the rendering neural network, a rendered image based on the initial image, according to the image transformation model.

Machine-learning based technique for fast image enhancement

An image sensor of an image capture device may capture an image. The captured image may be stored in a buffer of two or more previously-captured images. An oldest image of the two or more previously-captured images may be removed from the buffer. An aggregate image of the images in the buffer may be updated. This updating may involve subtracting a representation of the oldest image from the aggregate image, and adding a representation of the captured image to the aggregate image. A viewfinder of the image capture device may display a representation of the aggregate image.

Live updates for synthetic long exposures

Imaging systems can often gather higher quality information about a field of view than the unaided human eye. For example, telescopes may magnify very distant objects, microscopes may magnify very small objects, and high frame-rate cameras may capture fast motion. The present disclosure includes devices and methods that provide real-time vision enhancement without the delay of replaying from storage media. The disclosed devices and methods may include a live view display and image and other information enhancements, which utilize in-line computation and constant control. The disclosure includes techniques for enabling push-button slow motion effects through buffer management and the adjustment of a display frame rate.

Growing community of inventors

San Francisco, CA, United States of America

Jiawen Chen