Google Inc.

Massachusetts Institute of Technology

Samuel William Hasinoff

Ryan M Geiss

Marc Stewart Levoy

Changyin Zhou

Jiawen Chen

William T Freeman

Jonathan Tilton Barron

Frederic Durand

Tianfan Xue

Myers Abraham Davis

YiChang Shih

Peyman Milanfar

Chorong Johnston

Michelle Chen

Michael Gharbi

Sriram Thirthala

Rachit Gupta

Alexander Schiffhauer

Kelly Tsai

An example method includes displaying, by a graphical user interface of a computing device, an image comprising a target region. The target region may be smaller than an entirety of the image. The method includes providing, by the graphical user interface, a user-adjustable control to adjust a desired local brightness exposure level for the target region. The method includes receiving, by the user-adjustable control, a user indication of the desired local brightness exposure level for the target region. The method includes adjusting the local brightness exposure level for the target region in the image in response to the user indication.

Methods and systems for user adjustable region based brightness settings

Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.

Dual exposure control in a camera system

Display screen or portion thereof with a graphical user interface

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

In one embodiment, a method comprises projecting, from a projector, a diffused on an object. The method further includes capturing, with a first camera in a particular location, a reference image of the object while the diffused is projected on the object. The method further includes capturing, with a second camera positioned in the particular location, a test image of the object while the diffused is projected on the object. The method further includes comparing speckles in the reference image to the test image. The projector, first camera and second camera are removably provided to and positioned in a site of the object.

Laser speckle photography for surface tampering detection

A plurality of images of a scene may be obtained. These images may have been captured by an image sensor, and may include a first image and a second image. A particular gain may have been applied to the first image. An effective color temperature and a brightness of a first pixel in the first image may be determined, and a mapping between pixel characteristics and noise deviation of the image sensor may be selected. The pixel characteristics may include pixel brightness. The selected mapping may be used to map at least the brightness of the first pixel to a particular noise deviation. The brightness of the first pixel and the particular noise deviation may be compared to a brightness of a second pixel of the second image. The comparison may be used to determine whether to merge the first pixel and the second pixel.

Noise models for image processing

The present disclosure provides example methods operable by computing device. An example method can include receiving an image from a camera. The method can also include comparing one or more parameters of the image with one or more control parameters, where the one or more control parameters comprise information indicative of an image from a substantially unobstructed camera. Based on the comparison, the method can also include determining a score between the one or more parameters of the image and the one or more control parameters. The method can also include accumulating, by a computing device, a count of a number of times the determined score image exceeds a first threshold. Based on the count exceeding a second threshold, the method can also include determining that the camera is at least partially obstructed.

Camera obstruction detection

An image-stack viewer may switch between images in an image stack based on detected interactions with the images that are displayed in the viewer. In particular, a region-of-interest (ROI) in an image may be determined based on an interaction, and image characteristics of the ROI may be evaluated in two or more images in the image stack where the ROI best represents the evaluated characteristics.

Interactive viewer for image stacks

A first plurality of images of a scene may be captured. Each image of the first plurality of images may be captured with a different total exposure time (TET). Based at least on the first plurality of images, a TET sequence may be determined for capturing images of the scene. A second plurality of images of the scene may be captured. Images in the second plurality of images may be captured using the TET sequence. Based at least on the second plurality of images, an output image of the scene may be constructed.

Determining an image capture payload burst structure based on a metering image capture sweep

A base m&#xd7;n tile, X, of a base image of a scene, and an alternate m&#xd7;n tile, Y, of an alternate image of the scene may be obtained. An m&#xd7;n blend map, B, for X and Y may also be obtained. B(i,j) may take on a first value to refer to X(i,j), or a second value to refer to Y(i,j). An m&#xd7;n conflict map, C, for X and Y may further be obtained. C(i,j) may take on a third value where X(i,j) and Y(i,j) are within a threshold value of one another, or a fourth value where X(i,j) and Y(i,j) are not within the threshold value of one another. Based on B and C, the pixel values of X and Y may be merged to form an m&#xd7;n tile Z.

Image merging with blending

A first plurality of images of a scene may be captured. Each image of the first plurality of images may be captured using a different TET. Based at least on the first plurality of images, a long TET, a short TET, and a TET sequence that includes the long TET and the short TET may be determined. A second plurality of images of the scene may be captured. The images in the second plurality of images may be captured sequentially in an image sequence using a sequence of TETs corresponding to the TET sequence. Based on one or more images in the image sequence, an output image may be constructed.

Growing community of inventors

Mountain View, CA, United States of America

Samuel William Hasinoff