GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

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.

arXiv commentAccepted at ECCV 2022

References in corpus (12)

• Conditional Adversarial Domain Adaptation
• Revisiting Batch Normalization For Practical Domain Adaptation
• Submanifold Sparse Convolutional Networks
• Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
• Improving robustness against common corruptions by covariate shift adaptation
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Learning general and distinctive 3D local deep descriptors for point cloud registration
• SynthCity: A large scale synthetic point cloud
• A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
• Multi-step Online Unsupervised Domain Adaptation
• Online Adaptation through Meta-Learning for Stereo Depth Estimation
• SF-UDA${}^{3D}$: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection