Snap Inc.

Adobe, Inc.

Bytedance Inc.

Beijing Bytedance Network Technology Co., Ltd.

Eastman-kodak Company

Lemon Inc.

Kodak Alaris Inc.

Jianchao Yang

Jia Li

Zhe Lin

Ning Xu

Hailin Jin

Guohui Wang

Linjie Yang

Xuehan Xiong

Jonathan Worthen Brandt

Kevin Dechau Tang

Samuel Edward Hare

Linjie Luo

Rahul Bhupendra Sheth

Yuke Zhu

Nicholas Richard Allen

Sheldon Chang

Fedir Poliakov

Amer Shahnawaz

Maria Pavlovskaia

Scott David Cohen

Ning Zhang

Zhili Chen

Xiao Yang

Jing Liu

Nathan Litke

Daniel Szeto

Jose Jesus (Joseph) Paredes

Elya Shechtman

Jue Wang

Xin Lu

William Brendel

Jingcong Zhang

Shah Tanmay Anilkumar

Lidiia Bogdanovych

Jen-Chan Jeff Chien

Aseem Agarwala

Tony Mathew

Sarah Kong

Yuncheng Li

Jonathan Solichin

Xutao Lv

Travis Chen

Xiaoyu Wang

Yunzhu Li

Guang Chen

Wei Han

Yingzhen Yang

Yanran Wang

Jiebo Luo

Zhaowen Wang

Chen Fang

Jian Ren

Wilmot Wei-Mau Li

Xuchen Song

Zhuoyuan Chen

Xiaochen Lian

Haoze Li

Xiang Yu

Xiaohui Shen

Ketan Tang

Jie Yu

Zihao Chen

Yiheng Zhu

Haiying Cheng

Shihkuang Chu

Liyou Xu

Jonathan Krause

Ray McClure

Yuanlong Chen

Anda Li

Ke Ma

Jae-Pil Heo

Weikai Li

Beixin Hu

Zhangyang Wang

Thomas Le Paine

Weilin Huang

Jia Lia

A positioning model optimization method, an image-based positioning method and positioning device, and a computer-readable storage medium are provided. The positioning model optimization method includes: inputting a positioning model for a scene, the positioning model including a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud; determining, for each 3D point in the 3D point cloud, a plurality of neighboring points of the 3D point, and if a distance relationship between each of the plurality of neighboring points and the 3D point is smaller than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and outputting the optimized positioning model for the scene.

Positioning model optimization method, positioning method, positioning device, and storage medium

A positioning model optimization method, a positioning method, and a positioning device are provided. The positioning model optimization method includes: inputting a positioning model for a scene, the positioning model including a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud; calculating a significance of each 3D point in the 3D point cloud, and if the significance is greater than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and outputting the optimized positioning model for the scene.

Positioning model optimization method, positioning method, and positioning device

Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system communicates at least a portion of a first content collection to a first client device, and receives a first selection communication in response, the first selection communication identifying a first piece of content of the first plurality of pieces of content. The server analyzes analyzing the first piece of content to identify a set of context values for the first piece of content, and accesses accessing a second content collection comprising pieces of content sharing at least a portion of the set of context values of the first piece of content. In various embodiments, different content values, image processing operations, and content selection operations are used to curate the content collections.

Content navigation with automated curation

An animation processing method and apparatus, an electronic device and a storage medium, applied to a shader, the method including: acquiring an animation sample of a model unit; acquiring an external interaction parameter of an augmented reality model, where the augmented reality model includes a plurality of model units; and outputting the augmented reality model, and driving the animation sample of the model unit in the output augmented reality model according to the external interaction parameter. The animation sample of the model unit can be driven according to the external interaction parameter, so that animation of the model can be adjusted according to user operation, thereby improving usability.

Animation processing method and apparatus, electronic device and storage medium

An image effect implementing method is described herein that includes: acquiring a first image, recognizing a set object in the first image, and acquiring an augmented reality model corresponding to the set object; superimposing, according to coordinate information of pixels of the set object, the augmented reality model onto the first image to obtain a second image; and upon detection of a preset deformation event, controlling, according to a set deformation policy, at least one sub-model of the augmented reality model in the second image to deform, and displaying the deformed second image.

Image effect implementing method and apparatus, electronic device and storage medium

A list information display method and apparatus, an electronic device, and a storage medium are provided, the method includes: displaying list information in response to an information display operation triggered by a user; obtaining a real scene shooting image; and loading a plurality of types of information related to the list information into the real scene shooting image and display the real scene shooting image. Due to the use of virtual enhanced display technology, while the list information is displayed in the real scene shooting image, the plurality of types of information related to the list information are also displayed. On one hand, the user can obtain more information related to the list information while obtaining the list information, which improves the efficiency of information acquisition; and on the other hand, the user can obtain information in the real scene shooting image, which improves the visual effect and interactive experience.

Ranking list information display method and apparatus, and electronic device and storage medium

Systems and methods are provided for receiving, at a server computer, a plurality of content messages from a plurality of content sources, each content message comprising media content and associated with a predetermined media collection, for each of the plurality of content messages received, analyzing each of the plurality of content messages to determine a quality score for each of the plurality of content messages, and storing each of the plurality of content messages in a database along with the quality score for each of the plurality of content messages. The systems and methods further provided for receiving, from an operator device, a threshold percentage for the media collection, determining a subset of the plurality of content messages associated with the media collection to be made available to the operator device based on the threshold percentage received from the operator device and the quality score for each of the plurality of content messages, and causing only the subset of the plurality of content messages associated with media collection to be displayed on the operator device for the media collection.

Generation, curation, and presentation of media collections

A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

Modulated image segmentation

A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

Compact neural networks using condensed filters

A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Generating an image mask using machine learning

A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Real-time tracking-compensated image effects

Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system receives a plurality of content communications from a plurality of client devices, each content communication comprising an associated piece of content and a corresponding metadata. Each content communication is processed to determine associated context values for each piece of content, each associated context value comprising at least one content value generated by machine vision processing of the associated piece of content. A first content collection is automatically generated based on context values, and a set of user accounts are associated with the collection. An identifier associated with the first content collection is published to user devices associated with user accounts. In various additional embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.

Automated content curation and communication

Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

Adversarial network for transfer learning

Systems and methods are provided for receiving input increasing a default predetermined window of time that the new media collection is accessible and activating the new media collection for the increased predetermined window of time and a geographic boundary size for where media content originates. The systems and methods further cause a plurality of content messages comprising media content originating in the geographical boundary size to be included in the new media collection and displayed in response to a request from a computing device to view the new media collection based on determining the request occurs within the increased predetermined window of time that the new media collection is accessible.

Growing community of inventors

Los Angeles, CA, United States of America

Jianchao Yang