公开(公告)号：US20210390407A1

公开(公告)日：2021-12-16

申请号：US17344254

申请日：2021-06-10

Applicant: Waymo LLC

Inventor： Vincent Michael Casser ,  Yuning Chai ,  Dragomir Anguelov ,  Hang Zhao ,  Henrik Kretzschmar ,  Reza Mahjourian ,  Anelia Angelova ,  Ariel Gordon ,  Soeren Pirk

IPC: G06N3/08 ,  G06K9/62 ,  G06K9/00

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a perspective computer vision model. The model is configured to receive input data characterizing an input scene in an environment from an input viewpoint and to process the input data in accordance with a set of model parameters to generate an output perspective representation of the scene from the input viewpoint. The system trains the model based on first data characterizing a scene in the environment from a first viewpoint and second data characterizing the scene in the environment from a second, different viewpoint.

公开(公告)号：US20230110391A1

公开(公告)日：2023-04-13

申请号：US17956696

申请日：2022-09-29

Applicant: Waymo LLC

Inventor： Vincent Michael Casser ,  Bradley Dodson

IPC: G06T7/521

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining the visibility of query points using depth estimates generated by a neural network.

公开(公告)号：US20230334842A1

公开(公告)日：2023-10-19

申请号：US18136252

申请日：2023-04-18

Applicant: Waymo LLC

Inventor： Alex Zihao Zhu ,  Vincent Michael Casser ,  Henrik Kretzschmar ,  Reza Mahjourian ,  Soeren Pirk

IPC: G06V10/82 ,  G06V10/774

CPC classification number: G06V10/82 ,  G06V10/774

Abstract: Methods, systems, and apparatus for processing inputs that include video frames using neural networks. In one aspect, a system comprises one or more computers configured to obtain a set of one or more training images and, for each training image, ground truth instance data that identifies, for each of one or more object instances, a corresponding region of the training image that depicts the object instance. For each training image in the set, the one or more computers process the training image using an instance segmentation neural network to generate an embedding output comprising a respective embedding for each of a plurality of output pixels. The one or more computers then train the instance segmentation neural network to minimize a loss function.