3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This can significantly hinder the navigation capabilities of self-driving vehicles. This paper advances the state of the art in this research field. Our first contribution consists in analysing a new unexplored scenario in point cloud segmentation, namely Source-Free Online Unsupervised Domain Adaptation (SF-OUDA). We experimentally show that state-of-the-art methods have a rather limited ability to adapt pre-trained deep network models to unseen domains in an online manner. Our second contribution is an approach that relies on adaptive self-training and geometric-feature propagation to adapt a pre-trained source model online without requiring either source data or target labels. Our third contribution is to study SF-OUDA in a challenging setup where source data is synthetic and target data is point clouds captured in the real world. We use the recent SynLiDAR dataset as a synthetic source and introduce two new synthetic (source) datasets, which can stimulate future synthetic-to-real autonomous driving research. Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds (Code and synthetic datasets are available at https://github.com/saltoricristiano/gipso-sfouda).

GIPSO. Geometrically informed propagation for online adaptation in 3D LiDAR segmentation / Saltori, Cristiano; Krivosheev, Evgeny; Lathuiliére, Stéphane; Sebe, Nicu; Galasso, Fabio; Fiameni, Giuseppe; Ricci, Elisa; Poiesi, Fabio. - 13693 LNCS:(2022), pp. 567-585. (Intervento presentato al convegno 17th European Conference on Computer Vision, ECCV 2022 tenutosi a Tel Aviv; Israel) [10.1007/978-3-031-19827-4_33].

GIPSO. Geometrically informed propagation for online adaptation in 3D LiDAR segmentation

Fabio Galasso;Elisa Ricci;
2022

Abstract

3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This can significantly hinder the navigation capabilities of self-driving vehicles. This paper advances the state of the art in this research field. Our first contribution consists in analysing a new unexplored scenario in point cloud segmentation, namely Source-Free Online Unsupervised Domain Adaptation (SF-OUDA). We experimentally show that state-of-the-art methods have a rather limited ability to adapt pre-trained deep network models to unseen domains in an online manner. Our second contribution is an approach that relies on adaptive self-training and geometric-feature propagation to adapt a pre-trained source model online without requiring either source data or target labels. Our third contribution is to study SF-OUDA in a challenging setup where source data is synthetic and target data is point clouds captured in the real world. We use the recent SynLiDAR dataset as a synthetic source and introduce two new synthetic (source) datasets, which can stimulate future synthetic-to-real autonomous driving research. Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds (Code and synthetic datasets are available at https://github.com/saltoricristiano/gipso-sfouda).
2022
17th European Conference on Computer Vision, ECCV 2022
computer vision, machine learning, 3D, LiDAR, segmentation, domain adaptation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
GIPSO. Geometrically informed propagation for online adaptation in 3D LiDAR segmentation / Saltori, Cristiano; Krivosheev, Evgeny; Lathuiliére, Stéphane; Sebe, Nicu; Galasso, Fabio; Fiameni, Giuseppe; Ricci, Elisa; Poiesi, Fabio. - 13693 LNCS:(2022), pp. 567-585. (Intervento presentato al convegno 17th European Conference on Computer Vision, ECCV 2022 tenutosi a Tel Aviv; Israel) [10.1007/978-3-031-19827-4_33].
File allegati a questo prodotto
File Dimensione Formato  
Saltori_GIPSO_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 896.21 kB
Formato Adobe PDF
896.21 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1657985
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 2
social impact