Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds

TL;DR

This paper introduces a semi-supervised method for object classification in 3D point clouds that leverages synthetic data and domain adaptation techniques, achieving high accuracy without manual annotations.

Contribution

It proposes a novel semi-supervised cross-domain learning approach using synthetic models and augmentations, along with a new benchmark dataset for 3D point cloud classification.

Findings

Outperforms baseline and state-of-the-art methods in cross-domain settings

Effective synthetic data augmentation improves real-world generalization

Demonstrates robustness in both indoor and outdoor scenarios

Abstract

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models, e.g., DGCNN, PointNet++, on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability. The code and data will be available upon publishing.