Shanghaitech University

General Electric Company

Huawei Technologies Co., Limited

Tsinghua University

Xiamen University

Lan Xu

Jingyi Yu

Wei Guo

Qionghai Dai

Hui Wang

Lu Fang

Jay F Leonard

Wei Cheng

Minye Wu

Yebin Liu

Shijiang Liu

Mengqi Ji

Jialian Li

Chenglu Wen

Cheng Wang

Haimin Luo

A deep neural network based hair rendering system is presented to model high frequency component of furry objects. Compared with existing approaches, the present method can generate photo-realistic rendering results. An acceleration method is applied in our framework, which can speed up training and rendering processes. In addition, a patch-based training scheme is introduced, which significantly increases the quality of outputs and preserves high frequency details.

Hair rendering system based on deep neural network

Described herein are systems and methods for training machine learning models to generate three-dimensional (3D) motions based on light detection and ranging (LiDAR) point clouds. In various embodiments, a computing system can encode a machine learning model representing an object in a scene. The computing system can train the machine learning model using a dataset comprising synchronous LiDAR point clouds captured by monocular LiDAR sensors and ground-truth three-dimensional motions obtained from IMU devices. The machine learning model can be configured to generate a three-dimensional motion of the object based on an input of a plurality of point cloud frames captured by a monocular LiDAR sensor.

System and method of capturing three-dimensional human motion capture with LiDAR

Provided are a three-dimensional reconstruction method, apparatus and system of a dynamic scene, a server and a medium. The method includes: acquiring multiple continuous depth image sequences of the dynamic scene, where the multiple continuous depth image sequences are captured by an array of drones equipped with depth cameras; fusing the multiple continuous depth image sequences to establish a three-dimensional reconstruction model of the dynamic scene; obtaining target observation points of the array of drones through calculation according to the three-dimensional reconstruction model and current poses of the array of drones; and instructing the array of drones to move to the target observation points to capture, and updating the three-dimensional reconstruction model according to multiple continuous depth image sequences captured by the array of drones at the target observation points.

Dynamic scene three-dimensional reconstruction method, apparatus and system, server, and medium

The present disclosure relates to user plane link establishment methods. One example method includes sending, by a first base station, an obtaining request associated with user equipment to a second base station, receiving, by the first base station, a response message corresponding to the obtaining request, where the response message includes a peer address associated with the user equipment, and establishing, by the first base station and based on the peer address, a user plane link corresponding to the user equipment.

User plane link establishment method, base station, and mobility management device

A method for refurbishing a wind turbine includes positioning a new tower support mount on an existing foundation of the wind turbine, the existing foundation including an existing foundation pad and an existing tower support mount at least partially embedded in the existing foundation pad. The method further includes inserting a plurality of anchors through the new tower support mount.

Methods and apparatus for refurbishing wind turbine foundations

Growing community of inventors

Shanghai, China

Lan Xu