Qualcomm Incorporated

Apple Inc.

Microsoft Technology Licensing, LLC

Adobe, Inc.

Ebay, Incorporated

Nanome, Inc.

Yang Zhou

Ying Hai Chen

Ning Bi

Joonhyung Lim

Dingzeyu Li

Damien Albert Louis Coullon

Elya Shechtman

Hao Zhu

James Alexander Stryker

Deepali Aneja

Travis C Pedley

Michael Maczka

Jimei Yang

Florence W Ow

Jose Ignacio Echevarria Vallespi

Melody L Kuna

Taylor Harrison Gilbert

Ming Yu

Jun Saito

Guangtao Zhang

Xin Fu

Thomas R Matzinger

James C Wu

Brad Christopher Ciraulo

Jaime G Chavez Ruiz Garza

Haifeng Ji

Reza Arbabi

Qian Wang

Zezhong Zhang

Jack Pickup

Keyu Nie

Tao Yuan

Giorgio Ballardin

Liren Sun

Carrie Peng

Anthony Michael Ashcroft

Yu Long Cao

Matthew David Fisher

Yingyong Qi

Tao Pan

Richard Zhang

Duygu Ceylan Aksit

Aaron Albert Oro

Samir Mavji Shah

Nicholas R Trincia

Joshua A Hoover

Krishna Kumar Singh

Songtao Guo

Qigen Ji

Kai Wang

Taesung Park

Yi Zhou

Karthik Nagarajan

Charles W Werley

Ke-Li Cheng

Seul Bi Kim

Yangtuanfeng Wang

Geng Luo

Nicholas A Treadwell

Giorgio Gori

Ross D Arriens

Sara Rusignuolo

Shuai Zhang

Alexis Blevins Baird

Cody J White

Lili Wu

Lizabeth Li

Ivan Gavrenkov

Manas S Khadilkar

Bryan A Cloyd

Chen-Lan Chester Yen

Yi Wang

Muhammad Aatif Awan

Jenna L Withrow

Evangelos Kalogerakis

Sean M Cole

Randal W Lamore

Peter B Rusev

Steven Robert McCloskey

Albert Lingfeng Cui

Motohide Hatanaka

Raviraj Jain

Timothy C Wulff

Han-Tien Chang

Lixin Feng

Bhavana Chowdary Challa

Da Huo

Barry P Huang

Pal-Kristian Engstad

Erica M Lockheimer

Matthew Stoll

Qiannan Yin

Caitlin M Mclain

Qunzeng Liu

Leon Zilun Zhang

Zhan Xu

Peter J Guest

Nishant R Jayant

Vincent Brunet

Vivien Sin

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify two-dimensional images via scene-based editing using three-dimensional representations of the two-dimensional images. For instance, in one or more embodiments, the disclosed systems utilize three-dimensional representations of two-dimensional images to generate and modify shadows in the two-dimensional images according to various shadow maps. Additionally, the disclosed systems utilize three-dimensional representations of two-dimensional images to modify humans in the two-dimensional images. The disclosed systems also utilize three-dimensional representations of two-dimensional images to provide scene scale estimation via scale fields of the two-dimensional images. In some embodiments, the disclosed systems utilizes three-dimensional representations of two-dimensional images to generate and visualize 3D planar surfaces for modifying objects in two-dimensional images. The disclosed systems further use three-dimensional representations of two-dimensional images to customize focal points for the two-dimensional images.

Modifying poses of two-dimensional humans in two-dimensional images by reposing three-dimensional human models representing the two-dimensional humans

Embodiments are disclosed for generating a gesture reenactment video sequence corresponding to a target audio sequence using a trained network based on a video motion graph generated from a reference speech video. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input including a reference speech video and generating a video motion graph representing the reference speech video, where each node is associated with a frame of the reference video sequence and reference audio features of the reference audio sequence. The disclosed systems and methods further comprise receiving a second input including a target audio sequence, generating target audio features, identifying a node path through the video motion graph based on the target audio features and the reference audio features, and generating an output media sequence based on the identified node path through the video motion graph paired with the target audio sequence.

Generating gesture reenactment video from video motion graphs using machine learning

A server accesses a plurality of users' sessions with the web server. Each user session indicating a page flow of a corresponding user session for a plurality of web pages provided by the web server. The server generates a learning model using a neural network based on the plurality of users' sessions. The learning model is configured to predict a next user activity based on a current page flow of a current user session. The next user activity indicating one of continuing the current user session by visiting another web page provided by the web server and ending the current user session. The server dynamically adjusts a content of a web page based on the predicted next user activity.

System and method for improving user engagement based on user session analysis

The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine learning to generate a sequence of transition frames for a gap in a clipped digital video. For example, the disclosed system receives a clipped digital video that includes a pre-cut frame prior to a gap in the clipped digital video and a post-cut frame following the gap in the clipped digital video. Moreover, the disclosed system utilizes a natural motion sequence model to generates a sequence of transition keypoint maps between the pre-cut frame and the post-cut frame. Furthermore, using a generative neural network, the disclosed system generates a sequence of transition frames for the gap in the clipped digital video from the sequence of transition keypoint maps.

Utilizing generative models for resynthesis of transition frames in clipped digital videos

A magnetic alignment system can include a case with a magnetic alignment component that is configured to align with a magnetic alignment component of a wireless charging device. The case can support a portable electronic device, such as a smart phone and include an NFC coil for communicating with the portable electronic device. The magnetic alignment component and the NFC coil can be provided as an assembly that is embedded within a body of the case in a manner that provides a low profile and improved aesthetic appearance.

Case with magnetic alignment for portable electronic device

A strap may have a strip of material. A flexible magnet and other layers may be embedded between outer layers of the strip. The outer layers may be formed from leather or other natural materials, fabric, polymer, or other materials. The strap may have a snap mechanism that removably couples the strap to the item. The strip may have left and right portions that are coupled together using sliders and the snap mechanism. The sliders may be fixedly attached to respective end portions of left and right portions of the strip. A first of the sliders may have a slot that allows the first slider to slide along the right strip portion and a second of the sliders may have a slot that allows the second slider to slide along the left strip portion so that the length of the strap may be adjusted.

Adjustable straps with snaps and sliding clasps

Items such as enclosures may be provided with hidden magnets. An enclosure may be formed from a flexible housing layer. The flexible housing layer may be configured to open and close by folding around fold axes. Portions of the flexible layer may include a flexible base layer with openings. Flexible magnets may be embedded within the openings. The flexible magnets may be used in forming a magnetic clasp for the enclosure. The flexible magnets may each have a height and durometer value that closely matches the height and durometer value of an adjacent portion of the flexible base layer, thereby helping to hide the flexible magnets within the housing layer.

Items with hidden magnets

Embodiments are disclosed for articulated part extraction using images of animated characters from sprite sheets by a digital design system. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a plurality of images depicting an animated character in different poses. The disclosed systems and methods further comprise, for each pair of images in the plurality of images, determining, by a first machine learning model, pixel correspondences between pixels of the pair of images, and determining, by a second machine learning model, pixel clusters representing the animated character, each pixel cluster corresponding to a different structural segment of the animated character. The disclosed systems and methods further comprise selecting a subset of clusters that reconstructs the different poses of the animated character. The disclosed systems and methods further comprise creating a rigged animated character based on the selected subset of clusters.

Articulated part extraction from sprite sheets using machine learning

Accessories that can add new functionality to an electronic device. These accessories can provide additional functionality that allow for the replacement of a physical object that would otherwise be carried in addition to and separate from the electronic device. These accessories can further provide improvements, such as a reduction in size or improvement in functionality over the physical object to be replaced.

Magnetically attachable wallet

Embodiments of the present invention provide systems, methods, and computer storage media for generating an animation of a talking head from an input audio signal of speech and a representation (such as a static image) of a head to animate. Generally, a neural network can learn to predict a set of 3D facial landmarks that can be used to drive the animation. In some embodiments, the neural network can learn to detect different speaking styles in the input speech and account for the different speaking styles when predicting the 3D facial landmarks. Generally, template 3D facial landmarks can be identified or extracted from the input image or other representation of the head, and the template 3D facial landmarks can be used with successive windows of audio from the input speech to predict 3D facial landmarks and generate a corresponding animation with plausible 3D effects.

Style-aware audio-driven talking head animation from a single image

Embodiments are disclosed for re-timing a video sequence to an audio sequence based on the detection of motion beats in the video sequence and audio beats in the audio sequence. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input, the first input including a video sequence, detecting motion beats in the video sequence, receiving a second input, the second input including an audio sequence, detecting audio beats in the audio sequence, modifying the video sequence by matching the detected motions beats in the video sequence to the detected audio beats in the audio sequence, and outputting the modified video sequence.

Re-timing a video sequence to an audio sequence based on motion and audio beat detection

An accessory device for a portable electronic device is described. The accessory device includes a front cover connected to a back cover. The front cover includes multiple segments rotatable with respect to each other. The segments include magnets that allow the segments, through magnetic coupling, to couple with another segment or with the portable electronic device. When the front cover engages the back cover, a user may remove, or pull away, a segment from the back cover, causing the remaining segments to sequentially fall away from the back cover. In some instances, when the front cover at least partially engages the back cover, one of the segments includes magnets designed to couple with magnets in the back cover, but not with magnets in another segment. The accessory device may further include an opening that receives a camera assembly of the portable electronic device and forms a mechanical interlock.

Accessory cover for a portable electronic device

Systems, methods, and computer readable media to data drive a render graph are described. A render graph system defines one or more nodes for a render graph and one or more render targets associated with the nodes. The nodes includes one or more functions to define and resolve target handles for identifying render targets. The render graph system defines one or more connections between the nodes and render targets. The connection between the nodes and render targets form the render graph. The render graph system stores the render graph as a data file and converts, with a render graphics API, the data file into a render graph data object. The render graph system performs a frame setup phase the setups the render graph for a frame based on the render graph data object.

Customizable render pipelines using render graphs

Growing community of inventors

San Jose, CA, United States of America

Yang Zhou