Tencent America LLC

Weikai Chen

Bo Yang

Bo Wang

Songrun Liu

Xiaoxu Meng

A three-dimensional (3D) reconstruction method is provided. The method includes obtaining a two-dimensional (2D) pixel coordinate of a pixel in a 2D image of an object and a direction of a ray; projecting the 2D pixel coordinate to a 3D space to obtain a plurality of 3D points on the ray; for each 3D point of the plurality of 3D points: predicting a signed distance value for the 3D point; predicting a validity probability for the 3D point; and predicting an intensity value for the 3D point; obtaining a rendering loss based on the predicted signed distance values, the validity probabilities, and the intensity values of the plurality of 3D points to update a 3D reconstruction network; and extracting a 3D model of the object based on the updated 3D reconstruction network.

Three-dimensional reconstruction method and device, and storage medium

An electronic apparatus performs a method of recovering a complete and dense point cloud from a partial point cloud. The method includes: constructing a sparse but complete point cloud from the partial point cloud through a contrastive teacher-student neural network; and transforming the sparse but complete point cloud to the complete and dense point cloud. In some embodiments, the contrastive teacher-student neural network has a dual network structure comprising a teacher network and a student network both sharing the same architecture. The teacher network is a point cloud self-reconstruction network, and the student network is a point cloud completion network.

Growing community of inventors

Palo Alto, CA, United States of America

Weikai Chen