User: Guest  Login
Document type:
Konferenzbeitrag
Author(s):
Erçelik, Emeç; Yurtsever, Ekim; Liu, Mingyu; Yang, Zhijie; Zhang, Hanzhen; Topçam, Pınar; Listl, Maximilian; Kaan Çaylı, Yılmaz; Knoll, Alois
Title:
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
Abstract:
State-of-the-art 3D detection methods rely on supervised learning and large labelled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Against this backdrop, here we propose using a self-supervised training strategy to learn a general point cloud backbone model for downstream 3D vision tasks. 3D scene flow can be estimated with self-supervised learning using cycle consistency, which removes labell...     »
Book / Congress title:
European conference on computer vision (ECCV)
Year:
2022
Fulltext / DOI:
doi:https://doi.org/10.1007/978-3-031-20080-9_15
 BibTeX