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

by   Ziwei Wang, et al.

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.


page 1

page 2

page 3

page 4


MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

Point clouds have grown in importance in the way computers perceive the ...

Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

Point cloud processing and 3D shape understanding are very challenging t...

Classification of Aerial Photogrammetric 3D Point Clouds

We present a powerful method to extract per-point semantic class labels ...

Towards Open Set 3D Learning: A Benchmark on Object Point Clouds

In the last years, there has been significant progress in the field of 3...

Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentation

Current state-of-the-art point cloud-based perception methods usually re...

Quantifying point cloud realism through adversarially learned latent representations

Judging the quality of samples synthesized by generative models can be t...

Circular Accessible Depth: A Robust Traversability Representation for UGV Navigation

In this paper, we present the Circular Accessible Depth (CAD), a robust ...

Please sign up or login with your details

Forgot password? Click here to reset