Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds
This addresses the labeling bottleneck for applications like autonomous driving by enabling effective use of synthetic data, though it is incremental as it builds on existing point cloud encoding models.
The paper tackles the problem of labor-intensive labeling for 3D point cloud object classification by proposing a semi-supervised synthetic-to-real cross-domain learning approach that uses synthetic data from 3D models and achieves performance similar to fully-supervised methods, outperforming baselines and state-of-the-art approaches in cross-domain generalizability in indoor and outdoor settings.
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.