DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

TL;DR

This paper introduces DPGLA, a novel approach for unsupervised domain adaptation in 3D LiDAR semantic segmentation that effectively utilizes unlabeled data and reduces domain shift through dynamic pseudo-label filtering and data augmentation.

Contribution

The paper proposes DPLF and PG-DAP modules that improve synthetic-to-real domain adaptation in LiDAR segmentation, outperforming existing methods.

Findings

Achieves superior performance on synthetic-to-real segmentation tasks.

Demonstrates effectiveness of DPLF and PG-DAP through ablation studies.

Outperforms state-of-the-art methods in experiments.

Abstract

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic segmentation by leveraging synthetic point cloud data. However, we argue that existing methods do not effectively utilize unlabeled data, as they either rely on predefined or fixed confidence thresholds, resulting in suboptimal performance. In this paper, we propose a Dynamic Pseudo-Label Filtering (DPLF) scheme to enhance real data utilization in point cloud UDA semantic segmentation. Additionally, we design a simple and efficient Prior-Guided Data Augmentation Pipeline (PG-DAP) to mitigate domain shift between synthetic and real-world point clouds. Finally, we utilize data mixing consistency loss to push the model to learn context-free representations. We implement and thoroughly evaluate our approach through extensive comparisons with state-of-the-art methods. Experiments on two challenging synthetic-to-real point cloud semantic segmentation tasks demonstrate that our approach achieves superior performance. Ablation studies confirm the effectiveness of the DPLF and PG-DAP modules. We release the code of our method in this paper.