Google Inc.

Microsoft Technology Licensing, LLC

Massachusetts Institute of Technology

Adobe, Inc.

Ce Liu

William T Freeman

Michael Rubinstein

Aaron Joseph Maschinot

Richard Tucker

Michael Krainin

Dilip Krishnan

Forrester H Cole

Tali Dekel

Noah Snavely

Zhengqi Li

Aaron Yehuda Sarna

Piotr Teterwak

Sing Bing Kang

Daniel Pettigrew

Peyman Milanfar

Feng Yang

Jingyu Cui

Chen Wang

Huiwen Chang

Julia Winn

Yuanzhen Li

Mikaël Bonnevie

Abraham Stephens

Prannay Khosla

Yonglong Tian

Phillip John Isola

Richard S Szeliski

Wojciech Matusik

Paris Smaragdis

Sylvain Philippe Paris

Ming-Hsuan Yang

Jingbin Wang

Dominik Philemon Kaeser

Xiyang Luo

Mikael Bonnevie

Antonio Torralba Barriuso

Kevin Karsch

Yinxiao Li

Adam Tauman Kalai

David Salesin

Hossein Talebi

Pengchong Jin

Charles L Zitnick

Brian Curless

Omer Tamuz

Abhishek Kar

Ohad Shamir

Mike Krainin

Kyle Sargent

Haifeng Gong

Varun Jampani

Raanan Sayag

Wenchao Tong

Shuchao Bi

Yair Weiss

Ruohan Zhan

Serge J Belongie

Philip John Isola

Marshall Friend Tappen

Derek Debusschere

Michael Spencer Krainin

Mikael Pierre Bonnevie

Brain L Curless

Dominik Kaeser

William T Frreeman

Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

Compression-informed video super-resolution

The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

Supervised contrastive learning with multiple positive examples

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

Methods, systems, and computer programs encoded on a computer storage medium, that relate to extracting digital watermarks from images, irrespective of distortions introduced into these images. Methods can include inputting a first data item into a channel encoder that can generate a first encoded data item that is greater in length than the first data item and that (1) includes the input data item and (2) new data this is redundant of the input data item. Based on the first encoded data item and a first image, an encoder model can generate a first encoded image into which the first encoded data is embedded as a digital watermark. A decoder model can decode the first encoded data item to generate a second data, which can be decoded by the channel decoder to generate data that is predicted to be the first data.

Image watermarking

A multimedia communication system and computer-implemented method for transmitting auxiliary display content to an end-user communication device to be rendered on a display device with a special effect to emphasize an image included in the auxiliary display content, comprising a processor and a transmitter. The processor can be arranged to analyze image data included in an auxiliary display content, detect an object image or a background image in the auxiliary display content based on the analysis of the image data, determine a special effect based on the analysis of the image data, and apply the special effect to the auxiliary display content to modify display properties for the auxiliary display content such that the object image is emphasized or pops-out. The transmitter can be arranged to send the auxiliary display content with modified display properties to an end-user communication device. The special effect can comprise a non-customization special effect, a simple foreground special effect or a selective foreground special effect.

Display responsive communication system and method

A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.

Depth determination for images captured with a moving camera and representing moving features

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

Growing community of inventors

Arlington, MA, United States of America

Ce Liu