User: Guest  Login

Document type:
Konferenzbeitrag 
Author(s):
Alexander Lehner; Stefano Gasperini; Alvaro Marcos-Ramiro; Michael Schmidt; Mohammad-Ali Nikouei Mahani; Nassir Navab; Benjamin Busam; Federico Tombari 
Title:
3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection 
Abstract:
As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method’s detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous issues, such as the misdetection of damaged or rare cars. In this work, we substantially improve the generalization of 3D object detectors to out-of-domain data by deforming point clouds during trainin...    »
 
Keywords:
adversarial augmentation; domain generalization; out-of-distribution; point clouds; 3D object detection 
Dewey Decimal Classification:
000 Informatik, Wissen, Systeme 
Book / Congress title:
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 
Year:
2022 
Month:
Jun 
Reviewed:
ja 
Notes:
The first two authors contributed equally.