公开(公告)号：US20240169746A1

公开(公告)日：2024-05-23

申请号：US18161661

申请日：2023-01-30

Applicant: Salesforce, Inc.

Inventor： Manli Shu ,  Le Xue ,  Ning Yu ,  Roberto Martín-Martín ,  Juan Carlos Niebles Duque ,  Caiming Xiong ,  Ran Xu

IPC: G06V20/64 ,  G06T3/40 ,  G06V10/46 ,  G06V10/82

CPC classification number: G06V20/64 ,  G06T3/4007 ,  G06V10/46 ,  G06V10/82

Abstract: Embodiments described herein provide a system for three-dimensional (3D) object detection. The system includes an input interface configured to obtain 3D point data describing spatial information of a plurality of points, and a memory storing a neural network based 3D object detection model having an encoder and a decoder. The system also includes processors to perform operations including: encoding, by the encoder, a first set of coordinates into a first set of point features and a set of object features; sampling a second set of point features from the first set of point features; generating, by attention layers at the decoder, a set of attention weights by applying cross-attention over at least the set of object features and the second set of point feature, and generate, by the decoder, a predicted bounding box among the plurality of points based on at least in part on the set of attention weights.