Google Inc.

Massachusetts Institute of Technology

Quanta Computer Incorporated

Microsoft Technology Licensing, LLC

Michael Rubinstein

William T Freeman

Frederic Durand

Neal Wadhwa

Ce Liu

John V Guttag

Eugene Inghaw Shih

Hao-yu Wu

Inbar Mosseri

Tali Dekel

Oran Lang

Ariel Ephrat

Tianfan Xue

Daniel Pettigrew

Kevin William Wilson

Jingyu Cui

Avinatan Hassidim

Michael Krainin

Julia Winn

Aaron Joseph Maschinot

Abraham Stephens

Yossi Matias

Forrester H Cole

Junfeng He

Myers Abraham Davis

Kfir Aberman

Benjamin Schlesinger

Noam Etzion-Rosenberg

David Edward Jacobs

Yael Pritch Knaan

Amit Pitaru

Yukun Zhu

David Salesin

Kai Jochen Kohlhoff

Yossi Gandelsman

Mike Krainin

Anatoly Efros

Derek Debusschere

Israel Or Weinstein

Erika Lu

Tal Remez

Stella Laurenzo

David Henry Salesin

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

A computer-implemented method for decomposing videos into multiple layers () that can be re-combined with modified relative timings includes obtaining video data including a plurality of image frames () depicting one or more objects. For each of the plurality of frames, the computer-implemented method includes generating one or more object maps descriptive of a respective location of at least one object of the one or more objects within the image frame. For each of the plurality of frames, the computer-implemented method includes inputting the image frame and the one or more object maps into a machine-learned layer Tenderer model. () For each of the plurality of frames, the computer-implemented method includes receiving, as output from the machine-learned layer Tenderer model, a background layer illustrative of a background of the video data and one or more object layers respectively associated with one of the one or more object maps. The object layers include image data illustrative of the at least one object and one or more trace effects at least partially attributable to the at least one object such that the one or more object layers and the background layer can be re-combined with modified relative timings.

Re-timing objects in video via layered neural rendering

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

Audio-visual hearing aid

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: obtaining, for each frame in a stream of frames from a video in which faces of one or more speakers have been detected, a respective per-frame face embedding of the face of each speaker; processing, for each speaker, the per-frame face embeddings of the face of the speaker to generate visual features for the face of the speaker; obtaining a spectrogram of an audio soundtrack for the video; processing the spectrogram to generate an audio embedding for the audio soundtrack; combining the visual features for the one or more speakers and the audio embedding for the audio soundtrack to generate an audio-visual embedding for the video; determining a respective spectrogram mask for each of the one or more speakers; and determining a respective isolated speech spectrogram for each speaker.

Audio-visual speech separation

Example embodiments allow for fast, efficient motion-magnification of video streams by decomposing image frames of the video stream into local phase information at multiple spatial scales and/or orientations. The phase information for each image frame is then scaled to magnify local motion and the scaled phase information is transformed back into image frames to generate a motion-magnified video stream. Scaling of the phase information can include temporal filtering of the phase information across image frames, for example, to magnify motion at a particular frequency. In some embodiments, temporal filtering of phase information at a frequency of breathing, cardiovascular pulse, or some other process of interest allows for motion-magnification of motions within the video stream corresponding to the breathing or the other particular process of interest. The phase information can also be used to determine time-varying motion signals corresponding to motions of interest within the video stream.

Analysis and visualization of subtle motions in videos

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

The present disclosure relates to systems and methods for image capture. Namely, an image capture system may include a camera configured to capture images of a field of view, a display, and a controller. An initial image of the field of view from an initial camera pose may be captured. An obstruction may be determined to be observable in the field of view. Based on the obstruction, at least one desired camera pose may be determined. The at least one desired camera pose includes at least one desired position of the camera. A capture interface may be displayed, which may include instructions for moving the camera to the at least one desired camera pose. At least one further image of the field of view from the at least one desired camera pose may be captured. Captured images may be processed to remove the obstruction from a background image.

Taking photos through visual obstructions

An apparatus according to an embodiment of the present invention enables measurement and visualization of a refractive field such as a fluid. An embodiment device obtains video captured by a video camera with an imaging plane. Representations of apparent motions in the video are correlated to determine actual motions of the refractive field. A textured background of the scene can be modeled as stationary, with a refractive field translating between background and video camera. This approach offers multiple advantages over conventional fluid flow visualization, including an ability to use ordinary video equipment outside a laboratory without particle injection. Even natural backgrounds can be used, and fluid motion can be distinguished from refraction changes. Embodiments can render refractive flow visualizations for augmented reality, wearable devices, and video microscopes.

Devices for refractive field visualization

In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.

Linear-based Eulerian motion modulation

A method of recovering audio signals and corresponding apparatus according to an embodiment of the present invention using video or other sequence of images enables recovery of sound that causes vibrations of a surface. An embodiment method includes combining representations of local motions of a surface to produce a global motion signal of the surface. The local motions are captured in a series of images of features of the surface, and the global motion signal represents a sound within an environment in which the surface is located. Some embodiments compare representations of local motions of a surface to determine which motions are in-phase or out-of-phase with each other, enabling visualization of surface vibrational modes. Embodiments are passive, as compared to other forms of remote audio recovery that employ active sensing, such as laser microphone systems. Example applications for the embodiments include espionage and surveillance.

Method and apparatus for recovering audio signals from images

Linear-based eulerian motion modulation

An imaging method and corresponding apparatus according to an embodiment of the present invention enables measurement and visualization of fluid flow. An embodiment method includes obtaining video captured by a video camera with an imaging plane. Representations of motions in the video are correlated. A textured background of the scene can be modeled as stationary, with a refractive field translating between background and video camera. This approach offers multiple advantages over conventional fluid flow visualization, including an ability to use ordinary video equipment outside a laboratory without particle injection. Even natural backgrounds can be used, and fluid motion can be distinguished from refraction changes. Depth and three-dimensional information can be recovered using stereo video, and uncertainty methods can enhance measurement robustness where backgrounds are less textured. Example applications can include avionics and hydrocarbon leak detection.

Methods and apparatus for refractive flow measurement with three dimensions and uncertainty

Growing community of inventors

Somerville, MA, United States of America

Michael Rubinstein