-
Patent Agency Ranking
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
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.
-
公开(公告)号：US10762690B1
公开(公告)日：2020-09-01
申请号：US16272133
申请日：2019-02-11
Applicant: Apple Inc.
Inventor： Ibrahim Musba , Jizhou Gao , Jim Loup Zin , Andreas H. Bockert , Kjell Fredrik Larsson
Abstract: A method includes obtaining images, obtaining three-dimensional surface measurements, defining a three-dimensional mesh using the three-dimensional surface measurements, texturing the three-dimensional mesh using the images to define a textured three-dimensional mesh, identifying a first portion of the textured three-dimensional mesh, identifying a second portion of the textured three-dimensional mesh that obstructs visibility of part of the first portion of the textured three-dimensional mesh from an overhead perspective, and rendering a simulated overhead perspective image such that the second portion of the textured three-dimensional mesh is not represented in the simulated overhead perspective image.
-
公开(公告)号：US11189082B2
公开(公告)日：2021-11-30
申请号：US17007686
申请日：2020-08-31
Applicant: Apple Inc.
Inventor： Ibrahim Musba , Jizhou Gao , Jim Loup Zin , Andreas H. Bockert , Kjell Fredrik Larsson
Abstract: A method includes obtaining a three-dimensional model that represents a natural environment and identifying ground-level surfaces from the three-dimensional model, wherein the ground-level surfaces from the three-dimensional model represent ground-level features from the natural environment. The method also includes identifying overhanging features from the three-dimensional model, wherein the overhanging features from the three-dimensional model block visibility of the ground-level surfaces from the three-dimensional model when the ground-level surfaces are viewed from an orthographic perspective. The method also includes rendering a simulated image of the natural environment that includes at least some of the ground-level surfaces from the natural environment using a rendering system that generates the simulated image of the natural environment according to the orthographic perspective and ignores the overhanging features from the three-dimensional model so that the overhanging features from the three-dimensional model are omitted from the simulated image of the natural environment.
-
公开(公告)号：US20200258289A1
公开(公告)日：2020-08-13
申请号：US16272133
申请日：2019-02-11
Applicant: Apple Inc.
Inventor： Ibrahim Musba , Jizhou Gao , Jim Loup Zin , Andreas H. Bockert , Kjell Fredrik Larsson
Abstract: A method includes obtaining images, obtaining three-dimensional surface measurements, defining a three-dimensional mesh using the three-dimensional surface measurements, texturing the three-dimensional mesh using the images to define a textured three-dimensional mesh, identifying a first portion of the textured three-dimensional mesh, identifying a second portion of the textured three-dimensional mesh that obstructs visibility of part of the first portion of the textured three-dimensional mesh from an overhead perspective, and rendering a simulated overhead perspective image such that the second portion of the textured three-dimensional mesh is not represented in the simulated overhead perspective image.
-
-
-
-
Search Results
5
records
(took 0.013 seconds)
