公开(公告)号：US10936908B1

公开(公告)日：2021-03-02

申请号：US16869093

申请日：2020-05-07

Applicant: Apple Inc.

Inventor： Huy Tho Ho ,  Jingwei Wang ,  Kjell Fredrik Larsson

IPC: G06K9/62 ,  G06T7/11 ,  G06K9/00

Abstract: Systems and methods for semantic labeling of point clouds using images. Some implementations may include obtaining a point cloud that is based on lidar data reflecting one or more objects in a space; obtaining an image that includes a view of at least one of the one or more objects in the space; determining a projection of points from the point cloud onto the image; generating, using the projection, an augmented image that includes one or more channels of data from the point cloud and one or more channels of data from the image; inputting the augmented image to a two dimensional convolutional neural network to obtain a semantic labeled image wherein elements of the semantic labeled image include respective predictions; and mapping, by reversing the projection, predictions of the semantic labeled image to respective points of the point cloud to obtain a semantic labeled point cloud.

公开(公告)号：US20240404253A1

公开(公告)日：2024-12-05

申请号：US18422713

申请日：2024-01-25

Applicant: APPLE INC.

Inventor： Rahul Raguram ,  Vivek Roy ,  Shashank Tyagi ,  Huy Tho Ho ,  Kjell Fredrik Larsson

IPC: G06V10/774 ,  G06F21/62 ,  G06T7/73 ,  G06T11/00 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82

Abstract: Techniques are disclosed for training a feature extraction model. A computing device can receive a training image and generate noised feature vectors using a feature extraction model characterized by first parameters and taking the training image as input. The computing device can determine the noised feature vectors by at least determining a feature vector for individual pixels in the training image and applying noise to each feature vector. The computing device can generate a reconstructed image using a reconstructor model characterized by second parameters and taking the noised feature vectors as input. The computing device can determine a reconstruction loss by comparing the training image with the reconstructed image and a noise loss using the noise applied to each feature vector. The computing device can update the first parameters based on the noise loss.