公开(公告)号：US20250095173A1

公开(公告)日：2025-03-20

申请号：US18467035

申请日：2023-09-14

Applicant: QUALCOMM Incorporated

Inventor： Savitha Srinivasan ,  Varun Ravi Kumar ,  Senthil Kumar Yogamani

IPC: G06T7/50 ,  G06T5/00

Abstract: An example device for training a neural network includes a memory configured to store a neural network model for the neural network; and a processing system comprising one or more processors implemented in circuitry, the processing system being configured to: extract image features from an image of an area, the image features representing objects in the area; extract point cloud features from a point cloud representation of the area, the point cloud features representing the objects in the area; add Gaussian noise to a ground truth depth map for the area to generate a noisy ground truth depth map, the ground truth depth map representing accurate positions of the objects in the area; and train the neural network using the image features, the point cloud features, and the noisy ground truth depth map to generate a depth map.