CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding (CVPR'22)
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. It enables a 3D-2D correspondence of objects by maximizing agreement between point clouds and the corresponding rendered 2D image in the invariant space, while encouraging invariance to transformations in the point cloud modality. Our joint training objective combines the feature correspondences within and across modalities, thus ensembles a rich learning signal from both 3D point cloud and 2D image modalities in a self-supervised fashion. Experimental results show that our approach outperforms the previous unsupervised learning methods on a diverse range of downstream tasks including 3D object classification and segmentation. Further, the ablation studies validate the potency of our approach for a better point cloud understanding.
Refer to requirements.txt for the required packages.
CrossPoint pretrained models with DGCNN feature extractor are available here.
Datasets are available here. Run the command below to download all the datasets (ShapeNetRender, ModelNet40, ScanObjectNN, ShapeNetPart) to reproduce the results.
cd data
source download_data.sh
Refer to scripts/script.sh for the commands to train CrossPoint.
Run eval_ssl.ipynb notebook to perform linear SVM object classification in both ModelNet40 and ScanObjectNN datasets.
Refer to scripts/fsl_script.sh to perform few-shot object classification.
Refer to scripts/script.sh for fine-tuning experiment for part segmentation in ShapeNetPart dataset.