Self-Supervised Representation Learning on Point Clouds

GCPR 2023
T4V Workshop @ CVPR 2023

Computer Vision Group, Visual Computing Institute
RWTH Aachen University
* equal contribution

PCA projection of the learned representation of the 3D point cloud.


Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach. However, it remains open whether such a framework generalizes to the unique challenges of 3D point clouds. To answer this question, we extend data2vec to the point cloud domain and report encouraging results on several downstream tasks. In an in-depth analysis, we discover that the leakage of positional information reveals the overall object shape to the student even under heavy masking and thus hampers data2vec to learn strong representations for point clouds. We address this 3D-specific shortcoming by proposing point2vec, which unleashes the full potential of data2vec-like pre-training on point clouds. Our experiments show that point2vec outperforms other self-supervised methods on shape classification and few-shot learning on ModelNet40 and ScanObjectNN, while achieving competitive results on part segmentation on ShapeNetParts. These results suggest that the learned representations are strong and transferable, highlighting point2vec as a promising direction for self-supervised learning of point cloud representations.


Visualization of Learned Representations

We use PCA to project the learned representations into RGB space. Both a random initialization and data2vec–pc pre-training show a fairly strong positional bias, whereas point2vec exhibits a stronger semantic grouping without being trained on downstream dense prediction tasks.



  title={Point2Vec for Self-Supervised Representation Learning on Point Clouds},
  author={Abou Zeid, Karim and Schult, Jonas and Hermans, Alexander and Leibe, Bastian},
  journal={German Conference on Pattern Recognition (GCPR)},